© 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. 250589
    Prev
    Next
    INDEX
    Explanations

    words like nearest, want, repair, generally

    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
    Not in Any Lists

    No Comments

    Negative Logits
     plaît
    0.50
     chessboard
    0.50
     rozwiązania
    0.49
    谥
    0.49
     zakoń
    0.49
     quatern
    0.48
     clergyman
    0.48
     थरूर
    0.47
     chancellor
    0.47
     pratiquer
    0.47
    POSITIVE LOGITS
    ve
    0.61
     at
    0.53
    vega
    0.53
    ng
    0.50
     व
    0.50
    ada
    0.50
     is
    0.50
    ff
    0.50
    agg
    0.49
    ana
    0.48
    Activations Density 0.002%

    No Known Activations