© 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. 98288
    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
     в
    -1.13
     aesthetically
    -1.08
     יש
    -1.05
     intellectually
    -1.02
    ні
    -1.01
     созда
    -0.98
     ли
    -0.96
     من
    -0.96
     vocal
    -0.95
     Searches
    -0.94
    POSITIVE LOGITS
    ztes
    1.06
    㩒
    1.02
    るところ
    0.98
     SEPTEMBER
    0.98
     departement
    0.97
     แล้ว
    0.97
    も多く
    0.97
    咈
    0.96
     funcione
    0.96
     vilja
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.