© 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. 152832
    Prev
    Next
    INDEX
    Explanations

    file path components

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

    command prefixes and diagram separators

    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
    in
    0.68
    ARD
    0.60
    IN
    0.57
    ERS
    0.56
    ORN
    0.55
    OMAS
    0.54
     Januar
    0.53
    ：
    0.53
    ITOR
    0.52
    angor
    0.52
    POSITIVE LOGITS
    #!/
    0.62
    usr
    0.62
    to
    0.59
     انداز
    0.57
    يلي
    0.57
    ("/
    0.56
     entière
    0.56
    டும்
    0.56
    ल
    0.55
    ვ
    0.55
    Activations Density 0.023%

    No Known Activations