© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    foreign languages, punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Also
    0.40
     также
    0.39
    也可
    0.39
     Также
    0.38
    Также
    0.38
     also
    0.38
     역시
    0.37
    \
    0.37
     також
    0.36
     greatly
    0.36
    POSITIVE LOGITS
     těch
    0.46
     những
    0.44
     habitudes
    0.43
    那些
    0.41
    罅
    0.40
     마치
    0.39
     כמו
    0.39
     aquellas
    0.39
     subtleties
    0.39
    就像
    0.38
    Activations Density 0.031%

    No Known Activations