© 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. 10-GEMMASCOPE-RES-131K
    7. 22641
    Prev
    Next
    INDEX
    Explanations

    Serena Williams, Mombasa, favicon

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     have
    -2.48
    は
    -2.33
     et
    -2.23
    ’
    -2.19
    }
    -2.16
    医者
    -2.14
     touted
    -2.13
     raiſ
    -2.11
     of
    -2.08
    鵡
    -2.05
    POSITIVE LOGITS
    羕
    2.66
    魮
    2.64
    these
    2.44
    嵙
    2.41
    ised
    2.33
    銪
    2.33
    ጐ
    2.28
    尪
    2.27
    each
    2.25
     expériment
    2.20
    Activations Density 0.003%

    No Known Activations