© 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. 15745
    Prev
    Next
    INDEX
    Explanations

    graphql, interface, abstract, implements, fragment, input

    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
     doesn
    -1.34
     Doesn
    -1.27
     is
    -1.27
     SHOULD
    -1.24
     didn
    -1.20
     Should
    -1.19
    难道
    -1.19
     It
    -1.19
     from
    -1.18
     will
    -1.18
    POSITIVE LOGITS
    他們
    1.34
     their
    1.34
     sostenible
    1.20
    SHIRE
    1.17
    他們的
    1.16
     軍
    1.13
    various
    1.13
     atractiva
    1.11
    来年
    1.09
    meliharaan
    1.09
    Activations Density 0.041%

    No Known Activations