© 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. 116072
    Prev
    Next
    INDEX
    Explanations

    Chiang Kai-shek

    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
     ابتدائي
    0.63
     oublié
    0.62
    鼕
    0.61
    Catagory
    0.59
     গ্রহন
    0.58
    šanas
    0.57
     написано
    0.57
     म्हटले
    0.57
    šku
    0.57
    šla
    0.57
    POSITIVE LOGITS
    at
    0.98
    al
    0.94
    in
    0.87
    ent
    0.77
    an
    0.76
     T
    0.73
    os
    0.73
    p
    0.73
    he
    0.71
    it
    0.68
    Activations Density 0.003%

    No Known Activations