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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19454
    Prev
    Next
    INDEX
    Explanations

    field goal, kicking coach, sports points

    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
    /
    -2.05
    嘎
    -1.94
    to
    -1.92
     maroon
    -1.75
    f
    -1.74
    了一
    -1.73
    чков
    -1.70
     anadolu
    -1.68
     sekitarnya
    -1.66
    آوری
    -1.64
    POSITIVE LOGITS
    meteries
    2.13
     wodurch
    2.06
     to
    1.92
    ي
    1.86
    QMetaType
    1.77
     the
    1.77
     produziert
    1.74
     {
    
    1.73
    </h3>
    1.71
     abgeschlossen
    1.66
    Activations Density 0.001%

    No Known Activations