© 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. 26713
    Prev
    Next
    INDEX
    Explanations

    {$eq, [$eq], $gte, $gt, $match

    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
    écoute
    0.46
     রাণী
    0.40
     ബ്രിട്ട
    0.40
    íí
    0.40
    Tapi
    0.39
    聒
    0.38
    herst
    0.38
    ಣ್ಣ
    0.38
    anak
    0.36
    lán
    0.36
    POSITIVE LOGITS
     {$
    0.88
    {$
    0.86
    ={$
    0.72
     $
    0.63
     ['$
    0.63
     pipeline
    0.55
    gt
    0.55
     ($
    0.53
    /$
    0.53
    gte
    0.53
    Activations Density 0.003%

    No Known Activations