© 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. 68279
    Prev
    Next
    INDEX
    Explanations

    on weekday

    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
    ୌ
    -1.90
    帏
    -1.80
    熥
    -1.70
    ೢ
    -1.69
    🧐
    -1.69
    ໊
    -1.69
     prêtre
    -1.68
    ଃ
    -1.66
    ：……
    -1.65
    ⻬
    -1.63
    POSITIVE LOGITS
    .
    2.39
     last
    1.95
     time
    1.93
     hôm
    1.87
     ensure
    1.77
     still
    1.67
    ↵↵
    1.66
    1
    1.60
     allow
    1.59
     Thursday
    1.58
    Activations Density 0.048%

    No Known Activations