Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7785
    Prev
    Next
    INDEX
    Explanations

    Agent Dale Cooper in Twin Peaks

    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
     hemo
    -0.79
    bá
    -0.74
    adas
    -0.69
    เล
    -0.69
    zé
    -0.69
     Taz
    -0.69
     tundra
    -0.68
    Consequences
    -0.68
     tră
    -0.68
    sg
    -0.68
    POSITIVE LOGITS
     Twin
    1.34
     Lynch
    1.30
    Twin
    1.23
     Eraser
    1.14
    Lynch
    1.11
    DAVID
    1.00
     David
    0.92
    ツイン
    0.89
     Inland
    0.84
     Lumber
    0.84
    Activations Density 0.033%

    No Known Activations