© 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. 35228
    Prev
    Next
    INDEX
    Explanations

    Sunny, Kang, worn

    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
     Cumberland
    0.42
    Ku
    0.40
    Ку
    0.40
     পারবে
    0.39
    UCK
    0.39
    कु
    0.38
    Ờ
    0.38
     Ku
    0.38
    Puzzle
    0.38
     Kush
    0.37
    POSITIVE LOGITS
     अन्न
    0.42
     circuit
    0.42
    猙
    0.42
     halloween
    0.41
     tafel
    0.39
     runs
    0.38
    beatCounter
    0.38
     fis
    0.38
     moist
    0.38
     prophyl
    0.38
    Activations Density 0.001%

    No Known Activations