© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25656
    Prev
    Next
    INDEX
    Explanations

    robustness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    粄
    -2.38
     sélectionner
    -2.31
     ´
    -2.28
    
    -2.23
     vorigen
    -2.22
     cliquer
    -2.16
    蟥
    -2.16
    ܆
    -2.11
     дорогой
    -2.11
     unprecedented
    -2.11
    POSITIVE LOGITS
     of
    2.58
    \
    2.27
    ：《
    2.20
    ;
    2.05
    ly
    1.97
    8
    1.97
    );
    1.96
    IN
    1.92
     atau
    1.92
    綣
    1.88
    Activations Density 0.019%

    No Known Activations