© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16416
    Prev
    Next
    INDEX
    Explanations

    metadata and translations

    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
     from
    -1.80
     in
    -1.76
     for
    -1.73
     of
    -1.70
     turist
    -1.62
     to
    -1.58
     all
    -1.55
     as
    -1.48
     brune
    -1.45
     tigre
    -1.41
    POSITIVE LOGITS
     gött
    1.73
     hermosos
    1.59
     этих
    1.55
     osserv
    1.55
     sarà
    1.50
    きち
    1.45
     incrível
    1.45
    ኡ
    1.45
    trabajo
    1.42
     gigantic
    1.41
    Activations Density 0.002%

    No Known Activations