© 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. 110439
    Prev
    Next
    INDEX
    Explanations

    medium.com links and code

    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
    choc
    -0.79
     Adds
    -0.73
    彰
    -0.71
    тем
    -0.71
     ANSWER
    -0.71
    ित्र
    -0.69
    XJ
    -0.69
     geko
    -0.68
     Brady
    -0.67
    Bombay
    -0.67
    POSITIVE LOGITS
     larg
    0.63
    orsk
    0.63
    Esto
    0.62
    Demikian
    0.61
     Alone
    0.60
     steer
    0.60
    Formatting
    0.60
     wine
    0.60
    uminio
    0.59
    擴
    0.59
    Activations Density 0.046%

    No Known Activations