© 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. 221
    Prev
    Next
    INDEX
    Explanations

    profiles, ratings, specialties, portfolio

    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
    ループ
    0.42
     craftsmen
    0.41
    شنامه
    0.40
    acycl
    0.40
    ಶ್ಚ
    0.39
     artific
    0.39
    عی
    0.38
    実行
    0.38
    ઐ
    0.38
     علماء
    0.37
    POSITIVE LOGITS
     Profile
    0.68
     profile
    0.68
     rates
    0.67
     Rates
    0.66
     Biography
    0.64
     Ratings
    0.61
     specialties
    0.61
     Specialties
    0.61
     ratings
    0.59
     portfolio
    0.59
    Activations Density 0.000%

    No Known Activations