© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21318
    Prev
    Next
    INDEX
    Explanations

    matplotlib plotting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    blueprint
    0.39
    ેલી
    0.38
    ima
    0.38
    bhar
    0.38
    ｚ
    0.38
    ubah
    0.38
    jmath
    0.38
    umont
    0.38
    ína
    0.37
     переменную
    0.37
    POSITIVE LOGITS
     Sorry
    0.43
     Hare
    0.39
    硐
    0.39
     coincid
    0.38
     skewed
    0.38
     odd
    0.38
     pans
    0.38
     darn
    0.37
    Sorry
    0.37
    IsMethod
    0.37
    Activations Density 0.000%

    No Known Activations