© 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. 98418
    Prev
    Next
    INDEX
    Explanations

    poker and online gambling

    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
    んでる
    -0.82
     可愛い
    -0.77
     kuhusu
    -0.77
     ομά
    -0.75
     ním
    -0.72
     Nationals
    -0.71
    ⅔
    -0.71
    ATIONAL
    -0.71
    ゴルフ
    -0.69
    ⅓
    -0.69
    POSITIVE LOGITS
     poker
    1.39
    poker
    1.16
     Poker
    1.14
    Poker
    0.95
    圈
    0.91
     liquidity
    0.90
     Rake
    0.84
    player
    0.84
     rake
    0.82
     Alder
    0.81
    Activations Density 0.019%

    No Known Activations