© 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. 56279
    Prev
    Next
    INDEX
    Explanations

    event handling parameters

    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
     Mann
    0.40
    الو
    0.39
    Mann
    0.39
     রাজশাহ
    0.37
    ሟ
    0.37
     Jee
    0.37
    राष्ट्र
    0.37
     surviving
    0.36
     mann
    0.36
    ሪያ
    0.34
    POSITIVE LOGITS
    طيني
    0.40
     バイ
    0.40
     পাঠানোর
    0.40
     जल्द
    0.39
    遙
    0.39
     Unable
    0.39
     ಉಪಯೋಗ
    0.39
     заб
    0.39
     unavailability
    0.39
     REPLACE
    0.38
    Activations Density 0.002%

    No Known Activations