© 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. 22-GEMMASCOPE-RES-131K
    7. 127745
    Prev
    Next
    INDEX
    Explanations

    onCreate and onCreateDialog

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     einzeln
    -1.02
     их
    -0.95
     estableció
    -0.93
    Referințe
    -0.93
    炒め
    -0.91
    
    -0.90
     lanzó
    -0.88
     Reason
    -0.88
     encontrada
    -0.88
     dirigida
    -0.87
    POSITIVE LOGITS
     Voilà
    1.05
    纬
    1.02
     दू
    0.99
    íes
    0.98
     Poon
    0.96
     decoracion
    0.94
     acheteurs
    0.94
     ioe
    0.94
     Welles
    0.93
    ɳ
    0.93
    Activations Density 0.002%

    No Known Activations