© 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. 38427
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     probabilmente
    -1.23
     tinnitus
    -1.16
     Mô
    -1.16
     mangled
    -1.14
    ཿ
    -1.13
     Hvor
    -1.12
     keo
    -1.12
    ي
    -1.11
    
    -1.09
     Ukraina
    -1.09
    POSITIVE LOGITS
     increase
    1.21
     as
    1.13
     in
    1.13
     get
    1.10
     courir
    1.07
     Américas
    1.06
    ͣ
    1.05
     измерения
    1.04
    ภู
    1.04
     from
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.