© 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. 10-GEMMASCOPE-RES-131K
    7. 119577
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.28
     contará
    -1.62
    氩
    -1.60
     beberapa
    -1.58
    hassee
    -1.56
    撄
    -1.56
    causing
    -1.55
     mesmos
    -1.55
     encontrada
    -1.53
     لأن
    -1.51
    POSITIVE LOGITS
     perpetually
    1.77
    
    1.63
    There
    1.54
     incessant
    1.48
     constantly
    1.46
    Being
    1.46
    Almost
    1.45
    ),
    1.45
    цы
    1.42
     p
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.