© 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. 35191
    Prev
    Next
    INDEX
    Explanations

    running, runs, extend, criss, parallel

    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
    යට
    0.39
    芡
    0.38
     sentirse
    0.37
     helpless
    0.37
    ずつ
    0.36
     تعط
    0.36
     saluran
    0.36
    霎
    0.35
    沬
    0.35
    oser
    0.35
    POSITIVE LOGITS
     criss
    0.93
     intersect
    0.92
     runs
    0.91
     Runs
    0.88
     extends
    0.87
    runs
    0.87
     extend
    0.86
    延伸
    0.85
     parallel
    0.84
     running
    0.82
    Activations Density 0.004%

    No Known Activations