© 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. 58129
    Prev
    Next
    INDEX
    Explanations

    abbreviations like WR and PW

    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
     Which
    -3.00
    俛
    -2.98
    甞
    -2.95
    畱
    -2.92
    葙
    -2.83
    
    -2.81
    沨
    -2.80
     Subsequently
    -2.72
     Specifically
    -2.66
    岨
    -2.58
    POSITIVE LOGITS
    '
    3.50
    ),
    3.14
    of
    2.94
    enablog
    2.88
    窳
    2.64
    [
    2.55
    !
    2.34
    am
    2.34
    巿
    2.14
    攻擊
    2.11
    Activations Density 0.008%

    No Known Activations