© 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. 22-GEMMASCOPE-RES-131K
    7. 64417
    Prev
    Next
    INDEX
    Explanations

    code structure or positioning

    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
    Negative Logits
    เกี่ยวกับ
    -0.91
    gara
    -0.90
    مك
    -0.88
    Both
    -0.85
    лим
    -0.83
     “
    -0.81
    clientY
    -0.81
    فاض
    -0.81
    кот
    -0.80
     シリーズ
    -0.80
    POSITIVE LOGITS
     suivie
    0.98
     separating
    0.96
    zungs
    0.96
    mands
    0.95
    你觉得
    0.93
    bir
    0.92
    ﻜ
    0.91
     between
    0.91
    mvh
    0.90
     실패
    0.90
    Activations Density 0.003%

    No Known Activations