© 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. 22-GEMMASCOPE-RES-131K
    7. 15125
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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_22/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
     if
    -1.00
    そして
    -0.97
    тора
    -0.95
    あれば
    -0.95
    すけ
    -0.93
    кнуть
    -0.93
    Ὠ
    -0.92
    ва
    -0.91
     INCLUD
    -0.90
    </tr>
    -0.89
    POSITIVE LOGITS
     Stadtteil
    1.17
     Ortsteil
    1.07
    Aqui
    1.05
     нынеш
    1.04
     MA
    1.02
    nowu
    1.02
     ziemlich
    1.02
    Aç
    0.99
     
    0.98
     AMAZING
    0.98
    Activations Density 0.000%

    No Known Activations