© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74151
    Prev
    Next
    INDEX
    Explanations

    burn wounds and infections

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the word "burn" in various contexts including fire injuries, burnout, place names, and yoga programs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     คือ
    -2.56
    as
    -2.47
    
    -2.45
     Analyzing
    -2.45
    ﮭ
    -2.31
    ꯳
    -2.31
     剤
    -2.28
     godk
    -2.27
    ౧
    -2.25
    ay
    -2.23
    POSITIVE LOGITS
      
    2.69
    $
    2.66
    -
    2.61
     notoriously
    2.48
    さん
    2.39
     españ
    2.34
    1
    2.34
     freshly
    2.33
    ),
    2.27
    pingente
    2.27
    Activations Density 0.009%

    No Known Activations