© 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. 109765
    Prev
    Next
    INDEX
    Explanations

    signed routes

    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
    PATRICK
    -0.80
    師
    -0.71
    NavigationView
    -0.69
    Integration
    -0.69
    😅
    -0.68
     gotcha
    -0.67
     Cultivation
    -0.65
     Ancona
    -0.65
     😅
    -0.64
     patched
    -0.64
    POSITIVE LOGITS
     Roof
    0.73
    Enllaços
    0.73
    ĝo
    0.72
     maïs
    0.71
    tisch
    0.71
    diol
    0.70
    magin
    0.69
     avant
    0.69
    oute
    0.68
    marily
    0.67
    Activations Density 0.056%

    No Known Activations