© 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. 10917
    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
     all
    -2.06
     in
    -1.83
     almost
    -1.80
     both
    -1.78
     not
    -1.75
     one
    -1.73
     several
    -1.71
     more
    -1.71
     it
    -1.68
     some
    -1.66
    POSITIVE LOGITS
    皷
    1.67
     Dinas
    1.66
     Ejemplo
    1.59
     magnific
    1.58
     captivating
    1.55
     alluring
    1.55
    
    1.55
     horrid
    1.53
     magnificent
    1.52
     flamboyant
    1.50
    Activations Density 0.000%

    No Known Activations