© 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. 59950
    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
    ↵
    -2.44
     aislados
    -2.17
     cuyo
    -2.08
     cuya
    -1.99
     STILL
    -1.98
     renovables
    -1.98
     podría
    -1.93
    ל
    -1.92
     solemn
    -1.92
     asomb
    -1.88
    POSITIVE LOGITS
     菇
    1.95
    栒
    1.80
    饜
    1.79
    のね
    1.78
     juſ
    1.77
     itali
    1.72
    褙
    1.72
    {
    1.71
    があるので
    1.68
    鷓
    1.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.