© 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. 73263
    Prev
    Next
    INDEX
    Explanations

    pauses, interjections, and direct speech

    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
     maintenant
    -1.24
     trám
    -1.19
    我們
    -1.12
    盦
    -1.11
    あぁ
    -1.11
     Japão
    -1.11
    经常
    -1.10
    駸
    -1.09
     biens
    -1.08
    あー
    -1.08
    POSITIVE LOGITS
     by
    1.15
    数百
    1.10
     can
    1.09
     cannot
    1.02
     new
    1.02
     want
    1.00
     should
    0.95
    通し
    0.95
    んの
    0.95
     Normally
    0.93
    Activations Density 0.001%

    No Known Activations