© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9128
    Prev
    Next
    INDEX
    Explanations

    format specifiers

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Pyrimidine
    0.31
    جميع
    0.29
    สื่อ
    0.29
     иллю
    0.28
     капита
    0.27
    ്രീ
    0.27
    ПО
    0.27
    🤥
    0.27
    Seite
    0.26
     ஊழிய
    0.26
    POSITIVE LOGITS
     Similarly
    0.33
     other
    0.31
     altra
    0.29
     another
    0.29
     similarly
    0.28
     másik
    0.28
    另一个
    0.28
     otro
    0.28
     Stone
    0.27
     its
    0.27
    Activations Density 0.581%

    No Known Activations