© 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. 108789
    Prev
    Next
    INDEX
    Explanations

    special publications and events

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

    vanishing gradient

    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
     inspecting
    0.49
    اف
    0.49
     stools
    0.48
    銥
    0.48
    鵑
    0.48
    使用者
    0.48
    الق
    0.48
    闂
    0.46
     stool
    0.46
    闊
    0.45
    POSITIVE LOGITS
    corollary
    0.52
     Braves
    0.48
    ższ
    0.48
    yrı
    0.46
    windmill
    0.46
    zr
    0.46
     onları
    0.46
    кновен
    0.44
     Чтобы
    0.44
     बीसीसीआई
    0.44
    Activations Density 0.000%

    No Known Activations