© 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. 30032
    Prev
    Next
    INDEX
    Explanations

    title slide

    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
    袬
    0.37
     যাদের
    0.37
     ഉണ്ടാ
    0.36
     ወቅት
    0.35
    icação
    0.35
    kość
    0.35
    ungkin
    0.34
     zrobi
    0.34
    Ꮀ
    0.34
     సంద
    0.33
    POSITIVE LOGITS
     title
    2.72
     titular
    2.61
    title
    2.28
    Title
    2.27
     Title
    2.27
     tytu
    2.17
     TITLE
    2.16
     eponymous
    2.16
     titel
    2.13
    TITLE
    2.03
    Activations Density 0.002%

    No Known Activations