© 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. 114061
    Prev
    Next
    INDEX
    Explanations

    people names and team names

    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
     conceivably
    -2.47
    鄲
    -2.44
     マット
    -2.41
    y
    -2.41
    冬天
    -2.36
    夏天
    -2.27
     cerimonia
    -2.25
     Properly
    -2.22
     realistically
    -2.20
     Picchu
    -2.17
    POSITIVE LOGITS
    鸶
    2.95
     bym
    2.66
    硖
    2.55
    ization
    2.55
    薆
    2.50
     så
    2.41
     они
    2.39
    ме
    2.39
     две
    2.38
     dnes
    2.38
    Activations Density 0.006%

    No Known Activations