© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99804
    Prev
    Next
    INDEX
    Explanations

    HttpClient and web requests

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

    This neuron fires on technical tokens and class/method names associated with making HTTP requests (e.g. HttpClient, Get, request), i.e. instances of HTTP client–networking code.

    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
     свадеб
    -0.89
     wedding
    -0.89
     bridal
    -0.81
    Wedding
    -0.78
     vícti
    -0.77
     Wedding
    -0.76
     MySQL
    -0.76
    SQL
    -0.75
    jsonwebtoken
    -0.73
    orrhea
    -0.73
    POSITIVE LOGITS
     HttpClient
    2.05
    HttpClient
    1.83
     client
    1.40
     httpClient
    1.38
     Http
    1.33
    httpClient
    1.31
    client
    1.27
     axios
    1.17
     HTTP
    1.16
    Http
    1.10
    Activations Density 0.055%

    No Known Activations