© 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. 66597
    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
    eksi
    -0.98
     cinese
    -0.94
     sempurna
    -0.93
    Conclusión
    -0.92
     scarpe
    -0.90
     culturale
    -0.90
     lupa
    -0.89
     comunale
    -0.88
    нала
    -0.87
    Caratter
    -0.86
    POSITIVE LOGITS
     azok
    0.98
     regularmente
    0.94
     arginine
    0.92
     исче
    0.90
    regate
    0.89
    reys
    0.88
    chossen
    0.87
     erzeugen
    0.87
     mellem
    0.87
    CompilerServices
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.