© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2975
    Prev
    Next
    INDEX
    Explanations

    Col, col, and Kol prefixes

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ImageAlign
    0.43
    োক্ত
    0.42
    د
    0.41
    دخل
    0.38
    forcement
    0.38
    ungsl
    0.38
     perasaan
    0.37
    در
    0.37
    OLYBDENUM
    0.36
    ängel
    0.36
    POSITIVE LOGITS
    Col
    0.91
     col
    0.87
     Col
    0.83
     COL
    0.75
     коло
    0.73
     콜
    0.71
     colo
    0.70
    col
    0.68
     Kol
    0.66
     kol
    0.66
    Activations Density 0.028%

    No Known Activations