© 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. 32783
    Prev
    Next
    INDEX
    Explanations

    open daily or during business hours

    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
     that
    -1.35
     sanciones
    -1.29
     juzgar
    -1.27
    mathrm
    -1.20
     cauza
    -1.19
     cuando
    -1.17
    (!__
    -1.13
     complicaciones
    -1.10
     lesiones
    -1.09
     OGSÅ
    -1.09
    POSITIVE LOGITS
     to
    2.03
     for
    1.98
     enthou
    1.28
     simpel
    1.28
     sezon
    1.27
     statut
    1.24
     publie
    1.24
     Elé
    1.24
     medis
    1.23
     accepte
    1.20
    Activations Density 0.018%

    No Known Activations