© 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. 64321
    Prev
    Next
    INDEX
    Explanations

    status or completion indicators

    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
     of
    -1.10
     for
    -1.09
     Bewußt
    -0.95
    tadır
    -0.91
     Bestandteil
    -0.90
     ње
    -0.90
    ilangkan
    -0.89
    が
    -0.88
     Unterrichts
    -0.88
     Detalles
    -0.88
    POSITIVE LOGITS
     satisfe
    1.07
     domestiques
    1.01
    LinkedHashMap
    0.99
     tracción
    0.99
     success
    0.98
    early
    0.96
    queur
    0.95
     vélos
    0.94
     grasas
    0.94
     procéder
    0.94
    Activations Density 0.003%

    No Known Activations