© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68059
    Prev
    Next
    INDEX
    Explanations

    business consultants, research, materials, calculation

    np_acts-logits-general · gemini-2.5-flash-lite

    tactics trainer or puzzles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ProxyAgent
    0.42
     plugs
    0.40
     branches
    0.40
    หว่าง
    0.39
     chapters
    0.39
    नांक
    0.39
     cartridges
    0.38
     shoots
    0.38
     nostrils
    0.38
    鳃
    0.38
    POSITIVE LOGITS
     ডিজাই
    0.57
     тільки
    0.50
     باستخدام
    0.49
     روی
    0.49
     menggunakan
    0.49
     خير
    0.48
     Hanya
    0.47
     تنها
    0.47
     تعمیر
    0.47
     یک
    0.47
    Activations Density 0.001%

    No Known Activations