© 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. 64262
    Prev
    Next
    INDEX
    Explanations

    grateful, hugging, pass, unaware, claimed, concludes, gave, choosing

    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
    lliant
    -1.09
     they
    -1.05
     nossos
    -1.03
     we
    -1.03
    ffins
    -1.02
     órgãos
    -1.01
     ergän
    -0.96
     dirigió
    -0.93
     our
    -0.92
     chợ
    -0.92
    POSITIVE LOGITS
     his
    1.54
     categorie
    1.38
    lllll
    1.26
    lllllllll
    1.23
     Mawr
    1.23
     cerim
    1.21
     öf
    1.21
     acide
    1.16
    titud
    1.15
     vinci
    1.14
    Activations Density 0.078%

    No Known Activations