© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185463
    Prev
    Next
    INDEX
    Explanations

    references and publications

    np_acts-logits-general · gemini-2.5-flash-lite

    non-english words and academic terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    它是
    0.41
    Richard
    0.37
     Richard
    0.36
    waża
    0.36
    fre
    0.35
    后缀
    0.35
    意义
    0.34
    declar
    0.34
    |");
    0.34
     parecía
    0.33
    POSITIVE LOGITS
     unpublished
    0.45
     स्टील
    0.44
     乾燥
    0.41
     см
    0.40
     шт
    0.40
     Unpublished
    0.40
     秋冬
    0.40
     SW
    0.39
    året
    0.39
     تار
    0.38
    Activations Density 0.157%

    No Known Activations