© 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. 176186
    Prev
    Next
    INDEX
    Explanations

    system governance committees

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

    warnings and critical events

    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
     वापरा
    0.54
     nematode
    0.51
    astly
    0.48
     ridurre
    0.47
    ังสือ
    0.45
     αξ
    0.44
    兕
    0.44
    みた
    0.43
     варто
    0.43
    even
    0.43
    POSITIVE LOGITS
    щей
    0.48
    క్ష
    0.46
     reprogram
    0.45
    홍
    0.45
    AllWindows
    0.44
     anz
    0.44
    Cread
    0.43
    са
    0.43
     cleared
    0.43
     exchanged
    0.43
    Activations Density 0.001%

    No Known Activations