© 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. 15599
    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
     grise
    -1.18
     greco
    -1.14
     cilind
    -1.13
     lepro
    -1.09
     sila
    -1.06
     fasc
    -1.05
     nara
    -1.04
     vedo
    -1.02
     olu
    -1.02
     vru
    -1.02
    POSITIVE LOGITS
     naše
    1.19
     Kindheit
    1.02
    nikiem
    1.01
     wersja
    1.00
    [{\
    1.00
     oč
    0.98
     približ
    0.98
     offizi
    0.95
    叔叔
    0.95
     Konzert
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.