© 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. 34-GEMMASCOPE-RES-131K
    7. 90428
    Prev
    Next
    INDEX
    Explanations

    Olympic events, Romney, Sandy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     corks
    -0.73
     Rhea
    -0.71
    躙
    -0.70
     устраи
    -0.69
    Archi
    -0.68
    Fiche
    -0.68
     crece
    -0.68
     estimate
    -0.67
     disfru
    -0.66
    enterian
    -0.66
    POSITIVE LOGITS
     olymp
    0.96
     Olympic
    0.93
     Olympian
    0.88
     Romney
    0.85
     Olympics
    0.85
    Olympic
    0.82
     Paralympic
    0.81
    Sandy
    0.79
     Sandy
    0.79
     Mitt
    0.79
    Activations Density 0.074%

    No Known Activations