© 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. 216088
    Prev
    Next
    INDEX
    Explanations

    national policies, labor conditions

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

    voltage distribution

    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
    ם
    0.50
     方法
    0.48
    慎
    0.47
    نج
    0.47
     យើង
    0.46
    tig
    0.46
    }{|\
    0.46
     Фурга
    0.46
     工具
    0.46
    賂
    0.46
    POSITIVE LOGITS
     whatsoever
    0.52
     Barbados
    0.47
    at
    0.44
    cela
    0.44
     chatting
    0.44
     Bermuda
    0.43
     EXACT
    0.43
     warme
    0.43
     doctrine
    0.43
     Aruba
    0.43
    Activations Density 0.000%

    No Known Activations