© 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. 64520
    Prev
    Next
    INDEX
    Explanations

    code definitions with following brace

    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
     when
    -1.33
     Laufe
    -1.28
     Either
    -1.21
    ваясь
    -1.21
     from
    -1.20
    atação
    -1.19
     wybrać
    -1.19
     any
    -1.18
     and
    -1.17
    cuba
    -1.16
    POSITIVE LOGITS
    ここでは
    1.49
     остальные
    1.30
     expériences
    1.27
    1.22
    ,
    1.22
     côtes
    1.21
     comportements
    1.15
    Después
    1.13
    </u>
    1.12
    というわけで
    1.11
    Activations Density 0.001%
    No Known Activations