© 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. 21797
    Prev
    Next
    INDEX
    Explanations

    words starting with Ex

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

    This neuron detects the abbreviated “Ex” label that marks example or exemplary sections (e.g. “Ex. 1,” “Exemplary embodiments”) in technical or patent‐style documents.

    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
    J
    -3.30
    V
    -2.98
     
    -2.94
    C
    -2.80
    U
    -2.70
    H
    -2.67
        
    -2.50
     Некоторые
    -2.45
          
    -2.45
    та
    -2.41
    POSITIVE LOGITS
    ୈ
    3.23
    Ꮵ
    2.92
    鬭
    2.83
    メリカ
    2.81
    鶲
    2.77
    彣
    2.67
    ⃙
    2.58
    "}}>
    2.47
    
    2.42
    erintah
    2.39
    Activations Density 0.023%

    No Known Activations