© 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. 118161
    Prev
    Next
    INDEX
    Explanations

    foreign language characters or technical/formal terms

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

    specific requirements, common phrases

    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
     及
    0.59
    及
    0.49
     നമഃ
    0.48
     Грузии
    0.48
     Sistema
    0.47
     Pieter
    0.47
     reduz
    0.44
     desliz
    0.44
     gru
    0.43
     (%)
    0.43
    POSITIVE LOGITS
    interactions
    0.52
    Seat
    0.48
    buk
    0.48
    Connector
    0.47
    doors
    0.46
    attho
    0.46
    든
    0.46
    льти
    0.46
    แถ
    0.46
    ಮನ
    0.45
    Activations Density 0.001%

    No Known Activations