© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69019
    Prev
    Next
    INDEX
    Explanations

    recap analysis easier engage

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

    medical and technical processes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     mencari
    0.46
    본
    0.46
    Giải
    0.46
     Mazz
    0.44
    鎌
    0.44
    GlobalSection
    0.44
     Nept
    0.44
    ற்று
    0.43
     yardımcı
    0.43
    ّ
    0.43
    POSITIVE LOGITS
     straightened
    0.52
     differential
    0.50
     背景
    0.48
    ifically
    0.45
    ffic
    0.43
     ሁለት
    0.43
    ይል
    0.43
     攵
    0.42
     оборудование
    0.42
     رسمي
    0.42
    Activations Density 0.001%

    No Known Activations