© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83425
    Prev
    Next
    INDEX
    Explanations

    word three

    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
     systems
    -0.85
    vatel
    -0.81
    vation
    -0.77
    뤼
    -0.75
    તે
    -0.71
    clickable
    -0.71
     King
    -0.71
    rvats
    -0.71
     ч
    -0.70
     Kings
    -0.70
    POSITIVE LOGITS
     three
    0.99
     czter
    0.97
     ricks
    0.95
     трех
    0.94
     čtyř
    0.93
     üç
    0.90
    THREE
    0.89
    three
    0.88
    Three
    0.87
     trois
    0.87
    Activations Density 0.020%

    No Known Activations