What is adjusted response in logistic regression?

I am looking at at the Residuals section in the model class GeneralizedLinearModel (https://www.mathworks.com/help/stats/generalizedlinearmodel.html). I am trying to understand what exactly LinearPredictor residuals mean.

"LinearPredictor - Residuals on the linear predictor scale, equal to the adjusted response value minus the fitted linear combination of the predictors"

Specifically, in logistic regression, do they mean (1) "observed log odds minus the fitted linear combination of the predictors" or (2) the "working" residuals in the last iteration of the iterative weighted least squares?

I am trying to recreate "observed log odds" from the LinearPredictor residuals but I am not sure if this is possible at all. Thanks.

[Prince Kumar]

Hello,

Generalized Linear Model models allow to build a linear relationship between the response and predictors, even though their underlying relationship is not linear.

"LinearPredictor" gives the residual if the prediction has been done on linear scale. Thus it neither means (1) "observed log odds minus the fitted linear combination of the predictors" nor (2) the "working" residuals in the last iteration of the iterative weighted least squares?

You cannot create "observed log odds" from the "LinearPredictor" residuals.

Please refer Diagnostics section under Summary Statics in the page

https://in.mathworks.com/help/stats/generalizedlinearmodel.html