© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58357
    Prev
    Next
    INDEX
    Explanations

    social worker or worker

    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
     —
    -1.96
    $
    -1.84
    𖧵
    -1.84
    sandalia
    -1.80
     kimdir
    -1.70
    THEN
    -1.68
    媪
    -1.66
    xiii
    -1.61
     ſever
    -1.61
     ++;
    -1.59
    POSITIVE LOGITS
    ?”
    1.85
    Даже
    1.70
     Reverso
    1.68
     Daarna
    1.64
    ITAN
    1.62
     ▲
    1.61
    ديو
    1.60
    跄
    1.56
     taurus
    1.56
     こう
    1.55
    Activations Density 0.007%

    No Known Activations