© 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. 22-GEMMASCOPE-RES-131K
    7. 127935
    Prev
    Next
    INDEX
    Explanations

    not applicable, is decreased, effect of

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     voks
    -1.48
     vernis
    -1.29
    🐝
    -1.16
    resave
    -1.15
     Dí
    -1.15
     from
    -1.14
    YNAMIC
    -1.13
     mennesker
    -1.10
     sés
    -1.10
    всем
    -1.09
    POSITIVE LOGITS
    N
    1.41
    s
    1.31
    Y
    1.27
     myriad
    1.17
    P
    1.15
    S
    1.13
    H
    1.12
    F
    1.11
    w
    1.10
    st
    1.09
    Activations Density 0.000%

    No Known Activations