© 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. 67977
    Prev
    Next
    INDEX
    Explanations

    coupon or discount

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

    comparing meanings or quantities

    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
    /
    0.56
     inadequate
    0.52
     inadequacy
    0.52
     Duke
    0.49
    (
    0.48
     Rector
    0.47
     inadequ
    0.46
     invisibility
    0.46
     .
    0.46
     Archim
    0.46
    POSITIVE LOGITS
     डाउनलोड
    0.48
    chaoxing
    0.48
    larında
    0.47
     कट्टर
    0.47
     वैभव
    0.46
     ایکس
    0.46
    एक्स
    0.45
    र्जा
    0.45
    FilesIn
    0.45
    mainly
    0.45
    Activations Density 0.003%

    No Known Activations