© 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. 15634
    Prev
    Next
    INDEX
    Explanations

    ignoring things

    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
    derdag
    -1.80
    asanjo
    -1.61
    ссия
    -1.57
    owią
    -1.55
    TacToe
    -1.55
    溦
    -1.55
     δεν
    -1.54
    这样的
    -1.54
    nski
    -1.52
    さは
    -1.52
    POSITIVE LOGITS
     Redacción
    1.73
    or
    1.67
    
    1.66
    identical
    1.63
     iſt
    1.63
     cappuccio
    1.63
     mogę
    1.55
    ⸎
    1.55
     começaram
    1.54
     tinham
    1.52
    Activations Density 0.028%

    No Known Activations