© 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. 93958
    Prev
    Next
    INDEX
    Explanations

    HTTP request methods

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

    The neuron fires strongly on the document’s main title or heading line (e.g. the “Web Api 2.0 Routing – multiple actions matching” title).

    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
    requestBody
    -0.82
     body
    -0.75
     Bod
    -0.75
    RequestBody
    -0.75
     업
    -0.73
    敏
    -0.73
     updateUser
    -0.71
    ñadir
    -0.71
     Gor
    -0.70
    Contd
    -0.70
    POSITIVE LOGITS
     GET
    2.97
    GET
    2.67
     get
    1.97
    get
    1.93
    HttpGet
    1.88
     doGet
    1.81
    Get
    1.69
     Get
    1.57
    doGet
    1.45
    GetMapping
    1.37
    Activations Density 0.069%

    No Known Activations