© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16442
    Prev
    Next
    INDEX
    Explanations

    website domains and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ırlar
    -1.13
     тради
    -1.09
     fotó
    -1.08
     espagnol
    -1.07
     asisten
    -1.06
    を持っている
    -1.03
    érales
    -1.02
     évé
    -1.01
    ONESIA
    -1.00
    ırs
    -1.00
    POSITIVE LOGITS
     and
    1.45
     생
    1.07
     кілька
    1.05
    いくつかの
    1.05
     няколко
    1.02
    at
    0.96
     indietro
    0.95
    by
    0.94
    開心
    0.94
    まとめて
    0.93
    Activations Density 0.001%

    No Known Activations