© 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. 84025
    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
     якщо
    -1.15
     потім
    -1.05
    eben
    -0.95
     to
    -0.91
     tinta
    -0.89
     then
    -0.88
    さっそく
    -0.86
    的
    -0.86
    GetX
    -0.86
    Ṛ
    -0.85
    POSITIVE LOGITS
    啻
    1.14
     ninguno
    1.13
     unange
    1.13
     russischen
    1.12
     cualidades
    1.09
     rostros
    1.08
     leurs
    1.05
     zdecydow
    1.04
    くらいで
    1.03
     leyendo
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.