© 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. 198639
    Prev
    Next
    INDEX
    Explanations

    imports and exports

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

    import/export with product codes

    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
    पीरियंस
    0.51
     guérison
    0.49
     Saginaw
    0.48
    ᔾ
    0.48
    赟
    0.48
    ᓕ
    0.47
    壶
    0.47
    看起来
    0.47
     الاثنين
    0.47
     Greeley
    0.47
    POSITIVE LOGITS
     perfumes
    0.55
    Import
    0.55
     exported
    0.54
     Import
    0.53
     import
    0.53
     imported
    0.53
    成
    0.53
     mewah
    0.52
    imported
    0.50
    import
    0.50
    Activations Density 0.019%

    No Known Activations