© 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. 118922
    Prev
    Next
    INDEX
    Explanations

    asymptotic

    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
    owna
    -0.79
    Fit
    -0.72
     contigo
    -0.70
     Belgique
    -0.69
     Fits
    -0.69
     نوجوان
    -0.69
     genç
    -0.68
     SOLUTION
    -0.68
     Fit
    -0.67
    plain
    -0.67
    POSITIVE LOGITS
     asymptotic
    1.29
     Asympto
    1.00
     Sandwich
    0.93
     asymptotically
    0.93
    sandwich
    0.85
     sandwich
    0.83
    מלי
    0.81
     bias
    0.79
     asympto
    0.77
    Sandwich
    0.77
    Activations Density 0.041%

    No Known Activations