© 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. 45418
    Prev
    Next
    INDEX
    Explanations

    web cgi and Bolton

    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
    訁
    -2.97
     of
    -2.75
     แต่
    -2.63
    ſſen
    -2.59
     ถ้า
    -2.53
     也
    -2.45
    ,’”
    -2.44
    
    -2.44
    ’:
    -2.36
     configurações
    -2.36
    POSITIVE LOGITS
    但是在
    2.95
    但他
    2.64
    us
    2.59
    “
    2.58
    o
    2.58
     prioriti
    2.50
    但在
    2.41
    S
    2.36
     страшно
    2.34
    [
    2.30
    Activations Density 0.016%

    No Known Activations