© 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. 116895
    Prev
    Next
    INDEX
    Explanations

    processing server responses as JSON

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

    The neuron strongly activates on jQuery DOM-replacement calls—especially usages of the `replaceWith(...)` pattern.

    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
    Inputs
    -0.85
    =$("#
    -0.84
     détaillée
    -0.82
     MUNDO
    -0.82
    笘
    -0.80
    engkapi
    -0.80
    Leírás
    -0.79
     Cuevas
    -0.79
     unserer
    -0.78
     parents
    -0.78
    POSITIVE LOGITS
     response
    1.51
     JSON
    1.05
     Response
    1.00
    response
    0.96
     json
    0.88
    Response
    0.87
     responded
    0.87
     parser
    0.87
     Object
    0.86
     responds
    0.86
    Activations Density 0.007%

    No Known Activations