© 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. 207863
    Prev
    Next
    INDEX
    Explanations

    dear reader

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

    input and output limits

    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
     bane
    0.47
    arrows
    0.47
     suces
    0.46
    Después
    0.43
    ₦
    0.43
    Мы
    0.42
     ingl
    0.42
    €
    0.42
    Durante
    0.41
    ţă
    0.41
    POSITIVE LOGITS
     الإعلام
    0.57
    TextBoxColumn
    0.54
    getWriter
    0.53
     အရ
    0.47
     тексто
    0.45
     আসনের
    0.45
     تز
    0.44
     व्यव
    0.44
    勂
    0.44
     সম্ব
    0.44
    Activations Density 0.001%

    No Known Activations