© 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. 34-GEMMASCOPE-RES-131K
    7. 63409
    Prev
    Next
    INDEX
    Explanations

    sports statistics per game

    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
    artik
    -0.82
    prised
    -0.82
    SF
    -0.77
    ването
    -0.77
     fertili
    -0.77
    ڦ
    -0.77
     Volcano
    -0.75
     urat
    -0.75
    日目
    -0.75
    忌
    -0.75
    POSITIVE LOGITS
     game
    1.67
    game
    1.30
     games
    1.30
     outing
    1.13
    遊戲
    1.09
    ゲーム
    1.06
    Game
    0.98
    游戏
    0.93
     GAME
    0.93
    Games
    0.93
    Activations Density 0.003%

    No Known Activations