© 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. 16-GEMMASCOPE-2-RES-262K
    7. 90494
    Prev
    Next
    INDEX
    Explanations

    knight

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    z
    1.54
    n
    1.45
    ek
    1.37
    -
    1.37
    ’
    1.29
    '
    1.28
    ak
    1.27
    é
    1.25
    ↵
    1.23
    ov
    1.19
    POSITIVE LOGITS
    ０
    1.15
     in
    1.14
     to
    1.06
     в
    1.02
     knight
    1.01
    тера
    1.00
     прове
    0.97
    ۰
    0.93
     цело
    0.92
     Knight
    0.91
    Activations Density 0.002%

    No Known Activations