© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    code syntax terminators followed by keywords

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     AFFAIRS
    -1.53
     eleições
    -1.50
     secreta
    -1.42
     清新
    -1.36
    auces
    -1.36
    鹂
    -1.34
    啵
    -1.34
    
    -1.33
     ADVISORY
    -1.33
     CONSIDERATIONS
    -1.32
    POSITIVE LOGITS
     or
    2.00
    -
    1.59
    l
    1.54
    ?
    1.52
     because
    1.44
     ....
    1.41
     various
    1.39
    0
    1.39
     when
    1.38
     ONLY
    1.38
    Activations Density 0.050%

    No Known Activations