© 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. 105013
    Prev
    Next
    INDEX
    Explanations

    describing a condition

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

    This neuron activates on the word “condition,” especially when used in discussing or defining medical conditions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    UREAU
    -1.74
    趼
    -1.63
    nha
    -1.61
    cena
    -1.60
     You
    -1.59
    zahlung
    -1.57
    alna
    -1.57
    
    -1.57
    
    -1.56
     but
    -1.55
    POSITIVE LOGITS
     you
    2.45
    ↵↵
    1.86
     financieras
    1.73
     &
    1.70
     debes
    1.66
     besuchen
    1.66
     verschiedene
    1.63
    냑
    1.61
     unterscheiden
    1.60
     まし
    1.59
    Activations Density 0.052%

    No Known Activations