© 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. 10-GEMMASCOPE-RES-131K
    7. 114039
    Prev
    Next
    INDEX
    Explanations

    app->design->adminhtml->default->default->template

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

    zero-width or invisible Unicode characters, particularly zero-width spaces and similar formatting characters.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    以上です
    -1.80
    詳しくは
    -1.73
     GROSS
    -1.70
    เพราะ
    -1.66
    Приложение
    -1.66
     désigner
    -1.66
    棪
    -1.64
    今月
    -1.63
     sélections
    -1.62
     TANG
    -1.62
    POSITIVE LOGITS
     to
    2.28
    )
    1.95
    </strong>
    1.85
     feiern
    1.73
    ategori
    1.68
     revel
    1.66
    $;
    1.63
      
    1.59
     dzien
    1.59
     
    1.57
    Activations Density 0.001%

    No Known Activations