© 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. 68864
    Prev
    Next
    INDEX
    Explanations

    json objects and arrays

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

    This neuron detects JSON- or JavaScript-style object keys enclosed in quotation marks.

    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
    /");
    -1.84
    ꦮ
    -1.77
    ers
    -1.76
     ；
    -1.76
    летия
    -1.68
     最
    -1.63
     ");
    -1.62
    があります
    -1.56
     längre
    -1.52
     nästan
    -1.50
    POSITIVE LOGITS
    
    1.73
    趼
    1.73
    <bos>
    1.70
    </strong>
    1.69
    孤立
    1.67
     الرابع
    1.63
    coloriage
    1.62
    kệ
    1.60
     avait
    1.59
     identi
    1.58
    Activations Density 0.035%

    No Known Activations