© 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. 7230
    Prev
    Next
    INDEX
    Explanations

    JSON data processing

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

    This neuron detects references to JSON (e.g., literals like “JSON” or calls to JSON-related functions such as stringify, parse, dumps, encode).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     decoded
    -1.06
    Deserialize
    -1.00
    Deserializer
    -0.98
     Deserialize
    -0.96
    Decoded
    -0.96
     decode
    -0.93
    Unmarshal
    -0.89
     deserialize
    -0.88
     decoding
    -0.87
    deserialize
    -0.84
    POSITIVE LOGITS
    pX
    0.75
     Bắc
    0.74
    겠
    0.73
     Agra
    0.73
    絃
    0.73
    ) 
    0.72
    Agra
    0.72
    Encyclopedia
    0.71
    ');
    0.70
    embeds
    0.70
    Activations Density 0.009%

    No Known Activations