© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31262
    Prev
    Next
    INDEX
    Explanations

    json, response, and payload handling

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

    This neuron activates on occurrences of JSON-related code calls (e.g. “.json(…)” in various contexts).

    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
    蛱
    -1.07
    色々な
    -0.96
    辔
    -0.96
     неё
    -0.95
    geven
    -0.90
     pantalón
    -0.90
     هذه
    -0.89
    消失了
    -0.89
     wireType
    -0.88
     آزمون
    -0.88
    POSITIVE LOGITS
     with
    1.48
     what
    1.38
    ({
    1.27
     both
    1.22
     {
    1.22
     them
    1.20
    what
    1.00
     how
    0.96
     response
    0.96
    Both
    0.93
    Activations Density 0.001%

    No Known Activations