© 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. 15806
    Prev
    Next
    INDEX
    Explanations

    enclosing text in quotation marks

    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
     This
    -2.89
    內的
    -2.78
    ﮕ
    -2.58
     Your
    -2.55
     the
    -2.55
    裡的
    -2.41
    
    -2.38
    部分が
    -2.31
    厹
    -2.30
    傒
    -2.25
    POSITIVE LOGITS
    [
    2.84
    ).
    2.70
    ى
    2.39
     场
    2.38
    ,(
    2.31
    啸
    2.25
    графи
    2.22
    咴
    2.22
    
    2.19
    芎
    2.17
    Activations Density 0.008%

    No Known Activations