© 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. 90856
    Prev
    Next
    INDEX
    Explanations

    want to, identified on, should be, greater acceptance

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

    patterns of behavior or description

    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
     residential
    0.46
    ﻥ
    0.45
    지
    0.44
    рте
    0.44
    有力
    0.43
    住宅
    0.43
     “
    0.43
     RSA
    0.42
    工作
    0.42
    一座
    0.42
    POSITIVE LOGITS
     රස
    0.50
    បង្ហ
    0.50
    iqueness
    0.49
     ដ
    0.48
     जियोग्राफी
    0.48
     enchant
    0.48
     hooks
    0.47
     ende
    0.46
     danam
    0.46
     inz
    0.46
    Activations Density 0.000%

    No Known Activations