© 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. 25189
    Prev
    Next
    INDEX
    Explanations

    SEO and online marketing

    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
     "}";
    -1.73
     ")";
    -1.63
     But
    -1.49
    mueble
    -1.41
    .'</
    -1.37
    锨
    -1.34
    狃
    -1.33
     pleaſure
    -1.31
    
    -1.30
    ：(
    -1.30
    POSITIVE LOGITS
    ↵
    1.41
    ri
    1.38
    *
    1.30
    ra
    1.27
    _
    1.20
    resultSet
    1.16
    ch
    1.16
     reputations
    1.14
    in
    1.13
    ally
    1.10
    Activations Density 0.014%

    No Known Activations