© 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. 25143
    Prev
    Next
    INDEX
    Explanations

    css links and types

    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
     relata
    -1.36
     pousada
    -1.33
    깐
    -1.29
     concess
    -1.28
     blusa
    -1.28
     churras
    -1.27
     fabrica
    -1.27
     subje
    -1.25
     palestra
    -1.23
     sensibili
    -1.23
    POSITIVE LOGITS
     impresionantes
    1.36
     protože
    1.19
     okazji
    1.15
     hermosos
    1.14
     espectaculares
    1.13
     and
    1.12
    calcium
    1.11
     шесть
    1.09
     пять
    1.09
     aanzien
    1.08
    Activations Density 0.010%

    No Known Activations