© 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. 15344
    Prev
    Next
    INDEX
    Explanations

    ID, Class, Settlement, request, quality, guidelines, screw

    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
    тики
    -0.89
    /*
    -0.87
    单击
    -0.81
    R
    -0.78
    ليه
    -0.78
    r
    -0.78
    ({
    -0.77
    Apparently
    -0.77
     ح
    -0.76
    Required
    -0.74
    POSITIVE LOGITS
     nuovo
    0.99
     jugadores
    0.93
     gone
    0.92
    ształ
    0.90
    ͧ
    0.86
     otros
    0.85
     кабинет
    0.85
    疆
    0.82
    rimo
    0.81
    Jord
    0.80
    Activations Density 0.444%

    No Known Activations