© 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. 76244
    Prev
    Next
    INDEX
    Explanations

    playing board games

    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
     Duane
    -0.71
    Ǿ
    -0.69
    maintained
    -0.67
    萦
    -0.66
    PLICIT
    -0.65
    enosine
    -0.65
     punitive
    -0.65
    Klein
    -0.65
     organizations
    -0.65
     motocicleta
    -0.63
    POSITIVE LOGITS
     board
    3.20
     Monopoly
    2.75
     Board
    2.33
     BOARD
    2.31
    Board
    2.31
    board
    2.17
     monopoly
    2.17
    opoly
    2.00
    BOARD
    1.98
    ボード
    1.90
    Activations Density 0.037%

    No Known Activations