© 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. 82361
    Prev
    Next
    INDEX
    Explanations

    bronze silver gold medals

    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
     gold
    -1.00
     золо
    -0.93
     platinum
    -0.92
    Gold
    -0.88
    gold
    -0.84
     golden
    -0.84
     Platinum
    -0.84
    dian
    -0.82
     الجزء
    -0.79
    quait
    -0.79
    POSITIVE LOGITS
     medal
    1.49
    plated
    0.99
     medals
    0.98
     plated
    0.97
     medalist
    0.94
    Medal
    0.93
    medal
    0.87
    rierten
    0.87
     département
    0.84
    🥉
    0.84
    Activations Density 0.012%

    No Known Activations