© 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. 26156
    Prev
    Next
    INDEX
    Explanations

    Java main method

    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
     ventral
    0.41
     பாம்ப
    0.40
     mógł
    0.39
     бес
    0.38
     പ്രവർത്തന
    0.38
    峯
    0.38
     variously
    0.37
    𝑨
    0.37
     දු
    0.37
     prophecies
    0.36
    POSITIVE LOGITS
    语言
    0.45
     ভাষা
    0.42
    Commander
    0.41
     Language
    0.41
     language
    0.40
     redact
    0.39
    রিক
    0.39
     (){
    0.38
    Language
    0.38
     semicolon
    0.37
    Activations Density 0.000%

    No Known Activations