© 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-65K
    7. 56273
    Prev
    Next
    INDEX
    Explanations

    execute query

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Dar
    0.40
     Darren
    0.40
     Larn
    0.39
    ături
    0.39
    Dar
    0.39
     Darby
    0.39
     ज्ये
    0.38
    벚
    0.36
    Ꮭ
    0.36
     Darcy
    0.35
    POSITIVE LOGITS
    migrations
    0.49
     migrations
    0.40
     migration
    0.39
     вну
    0.39
     nos
    0.38
    Migration
    0.37
    }'.
    0.37
    पूर्वक
    0.37
     vás
    0.37
     ejecutar
    0.36
    Activations Density 0.001%

    No Known Activations