© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47863
    Prev
    Next
    INDEX
    Explanations

    http method requests

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

    This neuron detects HTTP method names (e.g. GET, POST, PATCH) and related numeric tokens such as status or error codes.

    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
    UNTAIN
    -0.89
     SECRETARY
    -0.86
    łami
    -0.85
    בות
    -0.83
     OREGON
    -0.81
     }}}
    -0.76
    alaska
    -0.76
     INFLUENCE
    -0.75
     potrebbero
    -0.73
     гле
    -0.73
    POSITIVE LOGITS
     request
    1.50
     method
    1.39
     requests
    1.28
    请求
    1.28
    リクエスト
    1.21
    request
    1.06
    requests
    1.02
    "../
    1.02
     methods
    1.00
     Method
    0.98
    Activations Density 0.024%

    No Known Activations