© 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. 81631
    Prev
    Next
    INDEX
    Explanations

    game outcomes and dynamics

    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
    funciones
    -0.86
    Its
    -0.84
     produzir
    -0.84
    都沒
    -0.81
     treatises
    -0.81
     hierzu
    -0.81
     réuss
    -0.80
    さに
    -0.80
     obiekt
    -0.79
     näch
    -0.79
    POSITIVE LOGITS
     game
    2.83
     games
    1.84
    ゲーム
    1.55
    游戏
    1.55
     proceedings
    1.51
    game
    1.50
    Game
    1.45
     contest
    1.42
    遊戲
    1.41
    比赛
    1.37
    Activations Density 0.016%

    No Known Activations