© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39771
    Prev
    Next
    INDEX
    Explanations

    week of the year

    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
    𖥧
    -2.08
     จาก
    -1.95
    yym
    -1.83
     好看
    -1.82
    yyb
    -1.81
    
    -1.80
    zembro
    -1.78
     escultura
    -1.73
    تیجه
    -1.73
    ’
    -1.70
    POSITIVE LOGITS
    ll
    2.55
    d
    2.52
    l
    2.48
    c
    2.33
    end
    2.31
    k
    2.30
    //
    2.09
     week
    2.06
    ian
    1.91
    week
    1.91
    Activations Density 0.102%

    No Known Activations