© 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. 10-GEMMASCOPE-RES-131K
    7. 68235
    Prev
    Next
    INDEX
    Explanations

    Mac OS X software

    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_10/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
     ")";
    -2.11
    om
    -1.95
     for
    -1.89
     "}";
    -1.87
    ).
    -1.86
     For
    -1.80
     на
    -1.78
    ep
    -1.75
    one
    -1.74
    );
    -1.73
    POSITIVE LOGITS
     complètement
    1.96
    𓁹
    1.96
     wahren
    1.91
     totalement
    1.88
     maravillosas
    1.88
     местах
    1.82
     Recent
    1.81
     semelh
    1.80
    着急
    1.80
     decidedly
    1.78
    Activations Density 0.023%

    No Known Activations