© 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. 10-GEMMASCOPE-RES-131K
    7. 771
    Prev
    Next
    INDEX
    Explanations

    Table schema or joining details

    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_10/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
    v
    -1.87
    However
    -1.72
    請繼續往下閱讀
    -1.68
    r
    -1.66
    n
    -1.62
     میشود
    -1.59
    p
    -1.59
    se
    -1.58
    begin
    -1.55
     şeyler
    -1.55
    POSITIVE LOGITS
     it
    2.17
    癀
    1.94
     a
    1.84
    瑒
    1.78
    羕
    1.77
    啻
    1.72
    鴬
    1.70
     często
    1.70
     continúas
    1.69
     abbiamo
    1.68
    Activations Density 0.001%

    No Known Activations