© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    request exception parameters

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

    The neuron activates on mentions of network/API request events or error handshakes (e.g. “request,” “handshake request,” “Request timed out”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    }^{+}$
    0.63
     объяв
    0.63
    Developed
    0.63
    Configurations
    0.61
     દો
    0.61
    pointA
    0.59
    高兴
    0.59
    Announcement
    0.59
    ▮
    0.58
     lancéolées
    0.58
    POSITIVE LOGITS
     request
    1.43
     Request
    1.30
    getRequest
    1.29
    request
    1.28
     REQUEST
    1.17
     请求
    1.15
     HttpRequest
    1.10
    REQUEST
    1.07
    请求
    1.04
     requests
    0.98
    Activations Density 0.047%

    No Known Activations