© 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. 83773
    Prev
    Next
    INDEX
    Explanations

    installing software or closing doors

    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
    s
    -1.99
     a
    -1.79
    Напомним
    -1.71
     is
    -1.50
     each
    -1.48
     zrobić
    -1.44
     ,
    -1.43
    l
    -1.41
    b
    -1.40
    m
    -1.38
    POSITIVE LOGITS
     Перейти
    1.68
     ogrom
    1.66
     maravillosas
    1.63
    蟊
    1.63
     ян
    1.63
     nacionales
    1.55
     maravill
    1.55
    jazd
    1.52
     rire
    1.52
     sustancias
    1.50
    Activations Density 0.084%

    No Known Activations