© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109758
    Prev
    Next
    INDEX
    Explanations

    Lumberjack, iban, Olig, Mechanisms, Y, Thursday, Okay

    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
     numeric
    -0.80
     atoi
    -0.77
    Ҭ
    -0.77
    öns
    -0.77
     redan
    -0.76
    hamdu
    -0.73
     Gül
    -0.73
    γη
    -0.73
    一杯
    -0.72
     кофе
    -0.71
    POSITIVE LOGITS
     principalement
    0.92
     również
    0.90
     Log
    0.89
     также
    0.89
    getLog
    0.88
     [$
    0.85
    abi
    0.82
    InvalidArgument
    0.81
     LOG
    0.81
    ุน
    0.81
    Activations Density 0.000%

    No Known Activations