© 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. 9432
    Prev
    Next
    INDEX
    Explanations

    equal

    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
     functioning
    0.48
    ّه
    0.47
    whose
    0.46
    の方法
    0.45
     operates
    0.44
    刖
    0.43
     whose
    0.42
    สัย
    0.42
     denominada
    0.42
    ُل
    0.42
    POSITIVE LOGITS
     differ
    0.76
     changed
    0.75
    changed
    0.67
     바뀌
    0.66
     determined
    0.61
     değiş
    0.61
     Changed
    0.61
     vary
    0.60
     измени
    0.60
     differs
    0.59
    Activations Density 0.002%

    No Known Activations