© 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. 26319
    Prev
    Next
    INDEX
    Explanations

    Korean celebrities and dramas

    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
    Negative Logits
     можете
    0.52
     نقص
    0.42
    ينات
    0.40
     يمكنك
    0.40
    櫥
    0.40
     प्रकाशित
    0.39
    আপনি
    0.39
     таких
    0.39
     хотите
    0.39
    みます
    0.39
    POSITIVE LOGITS
    한편
    0.57
     meanwhile
    0.50
     zaś
    0.49
     événement
    0.49
    ['
    0.47
    与此同时
    0.46
     Meanwhile
    0.46
     sementara
    0.45
     배우
    0.43
     권
    0.42
    Activations Density 0.000%

    No Known Activations