© 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. 9423
    Prev
    Next
    INDEX
    Explanations

    minimal dependencies

    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
    անի
    0.52
     geomét
    0.51
    <unused706>
    0.50
     മിക
    0.49
    溼
    0.48
     pigmented
    0.48
    <unused726>
    0.48
    <unused670>
    0.47
     nông
    0.47
     inhomogeneous
    0.47
    POSITIVE LOGITS
    p
    0.54
    sp
    0.52
     _
    0.51
    k
    0.51
    in
    0.50
    1
    0.49
    re
    0.49
    לי
    0.49
     Fund
    0.49
    sc
    0.47
    Activations Density 0.005%

    No Known Activations