© 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. 118957
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    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
    лада
    -0.73
    Macros
    -0.72
    malen
    -0.72
    execSQL
    -0.67
    \@
    -0.66
    benzene
    -0.66
    Maz
    -0.66
     建設
    -0.65
    InstanceId
    -0.64
    Rec
    -0.63
    POSITIVE LOGITS
     Quicks
    0.68
     Sust
    0.66
    utri
    0.66
     populate
    0.64
     replied
    0.63
    Swipe
    0.63
     поддержи
    0.61
     Egyes
    0.61
    Andrés
    0.61
    ライター
    0.60
    Activations Density 0.061%

    No Known Activations