© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118572
    Prev
    Next
    INDEX
    Explanations

    public services and places

    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_34/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
     gesamten
    -0.75
    Trades
    -0.75
     voisins
    -0.72
    Patriot
    -0.72
    fragments
    -0.71
     کیک
    -0.70
    Viki
    -0.70
    בות
    -0.68
    лочка
    -0.68
    ambiguous
    -0.68
    POSITIVE LOGITS
     Realm
    0.81
     realm
    0.80
    ubat
    0.77
     Widodo
    0.73
     artworks
    0.73
    煌
    0.73
     Oriental
    0.72
    Art
    0.71
    realm
    0.71
    TAKT
    0.71
    Activations Density 0.044%

    No Known Activations