© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75244
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     konkrét
    -1.33
     ganadores
    -1.13
     tatsächlich
    -1.13
    鴴
    -1.11
     dringend
    -1.02
     spéciaux
    -1.02
     geändert
    -1.02
     verarbeitet
    -1.02
     limpiar
    -1.02
     beträ
    -1.02
    POSITIVE LOGITS
     then
    1.40
     both
    1.30
     will
    1.20
     now
    1.15
     without
    1.14
     should
    1.12
     also
    1.08
     chiefly
    1.05
     this
    0.99
     continuously
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.