© 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. 104432
    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
     saisi
    -1.12
    istungen
    -1.02
    deutschland
    -0.95
     ček
    -0.94
    örü
    -0.93
    información
    -0.92
     invierno
    -0.92
     prób
    -0.91
     Pourquoi
    -0.90
     governador
    -0.89
    POSITIVE LOGITS
     vzh
    1.00
     البر
    0.92
    фов
    0.88
    ană
    0.87
    ensical
    0.86
    utenants
    0.86
    aneously
    0.84
    UTELY
    0.84
    iu
    0.84
    land
    0.83
    Activations Density 0.000%

    No Known Activations