© 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. 57525
    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
     perpetually
    -1.61
    
    -1.52
     incessant
    -1.48
     NOW
    -1.46
     I
    -1.45
     m
    -1.45
     constantly
    -1.41
     p
    -1.41
    на
    -1.41
    цы
    -1.41
    POSITIVE LOGITS
     to
    1.91
     contará
    1.65
    氩
    1.63
    hassee
    1.62
     realizará
    1.59
     لأن
    1.57
     encontrada
    1.56
     beberapa
    1.55
    撄
    1.55
    鲎
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.