© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65122
    Prev
    Next
    INDEX
    Explanations

    players sitting out or on the bench

    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
    لينا
    -0.78
     detected
    -0.76
     zoll
    -0.75
    ụp
    -0.73
     Serenity
    -0.72
    Adaptor
    -0.71
    情報は
    -0.68
    rahi
    -0.67
     leher
    -0.67
    tillerie
    -0.67
    POSITIVE LOGITS
     bench
    3.45
     Bench
    2.48
    Bench
    2.48
    bench
    2.44
     benches
    2.09
    BENCH
    1.91
    ベンチ
    1.62
     sitting
    1.48
     ben
    1.39
    Sitting
    1.36
    Activations Density 0.017%

    No Known Activations