© 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. 107959
    Prev
    Next
    INDEX
    Explanations

    bench press

    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
    윅
    -0.76
    asco
    -0.73
    abr
    -0.69
    groovy
    -0.68
    ⏪
    -0.68
    magini
    -0.66
    拯救
    -0.66
    selaer
    -0.66
    齬
    -0.66
    út
    -0.65
    POSITIVE LOGITS
     bench
    3.30
     Bench
    2.63
    Bench
    2.50
    bench
    2.50
     squat
    2.20
     dead
    2.00
    BENCH
    1.81
    ベンチ
    1.77
     Squat
    1.77
     lifts
    1.74
    Activations Density 0.042%

    No Known Activations