© 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. 16455
    Prev
    Next
    INDEX
    Explanations

    <!DOCTYPE HTML, Q:, Vital Topics:, A lawsuit

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kado
    -1.25
     asfalto
    -1.21
    галда
    -1.07
    tiara
    -1.07
     balas
    -1.05
     revolucion
    -1.05
    yta
    -1.05
    ceng
    -1.05
    kese
    -1.04
    siyah
    -1.03
    POSITIVE LOGITS
    j
    1.31
    r
    1.23
    is
    1.20
    ij
    1.20
    al
    1.17
    h
    1.15
    C
    1.13
    re
    1.12
    k
    1.11
    H
    1.10
    Activations Density 0.000%

    No Known Activations