© 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. 235712
    Prev
    Next
    INDEX
    Explanations

    measures and numbers

    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
     встречи
    0.44
    ziehung
    0.44
     ఒకటి
    0.44
    gebnisse
    0.43
    的有
    0.42
     persisting
    0.42
     impurities
    0.41
     आतंकी
    0.41
    ﻀ
    0.41
    జే
    0.41
    POSITIVE LOGITS
     თავ
    0.49
    numberOf
    0.45
     amd
    0.45
    ar
    0.44
    anyika
    0.44
     Namibia
    0.43
     Tudo
    0.42
     Tasmania
    0.42
    ای
    0.41
    ایت
    0.41
    Activations Density 0.001%

    No Known Activations