© 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. 72065
    Prev
    Next
    INDEX
    Explanations

    HTML entities and escaped characters

    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
     it
    -1.91
     by
    -1.79
     have
    -1.68
     at
    -1.60
     where
    -1.57
     when
    -1.55
     so
    -1.51
    唯有
    -1.51
    ↵
    -1.48
     there
    -1.48
    POSITIVE LOGITS
     réessayer
    1.91
    茈
    1.90
    
    1.82
     cérami
    1.77
     spp
    1.73
    ⱼ
    1.72
     compéti
    1.70
    ÜN
    1.70
     intégral
    1.70
     gratuites
    1.69
    Activations Density 0.021%

    No Known Activations