© 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. 6914
    Prev
    Next
    INDEX
    Explanations

    special teams

    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
    Negative Logits
     that
    -2.08
     other
    -1.80
     Who
    -1.70
    象征
    -1.52
     information
    -1.52
    世間
    -1.51
     What
    -1.46
     dozens
    -1.42
     various
    -1.39
     After
    -1.39
    POSITIVE LOGITS
     também
    1.42
     Tras
    1.40
     ยัง
    1.39
    passen
    1.36
     صفحۀ
    1.32
    一
    1.31
     '|
    1.30
    퐼
    1.30
     bañera
    1.28
    ႐
    1.28
    Activations Density 0.002%

    No Known Activations