© 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. 66173
    Prev
    Next
    INDEX
    Explanations

    medal table

    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
    utsal
    -0.78
    謹
    -0.74
    Є
    -0.73
    ギュラー
    -0.73
    定
    -0.70
    length
    -0.70
    SafeMath
    -0.69
    pá
    -0.69
    cista
    -0.68
     године
    -0.68
    POSITIVE LOGITS
     medal
    1.30
     medals
    1.26
    Tally
    1.23
     tally
    1.13
     меда
    1.08
    Medal
    1.02
     Tally
    1.02
     delegation
    1.02
    medal
    0.95
     delegations
    0.92
    Activations Density 0.010%

    No Known Activations