© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    bile transport, digestion, and excretion

    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
    耧
    0.44
    ंगाना
    0.44
    胭
    0.43
    Truck
    0.43
    弑
    0.42
    arrerol
    0.42
    簋
    0.41
    馚
    0.41
    onym
    0.41
    र्ती
    0.41
    POSITIVE LOGITS
     bile
    2.09
     Bile
    1.77
     biliary
    1.70
    bile
    1.63
     gallbladder
    1.45
     liver
    1.42
    胆
    1.34
     hepatic
    1.33
     chol
    1.29
     hepatocytes
    1.29
    Activations Density 0.015%

    No Known Activations