© 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. 10-GEMMASCOPE-RES-131K
    7. 3876
    Prev
    Next
    INDEX
    Explanations

    curl command and options

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

    The neuron fires on mentions of cURL—especially calls and constants like curl_init, curl_setopt, and CURLOPT_*—in 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_10/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
     But
    -2.77
     แต่
    -2.14
    lcl
    -2.09
     ejecuta
    -2.08
     लेकिन
    -2.08
    ,//
    -1.98
     ($("#
    -1.94
     Setelah
    -1.93
    荃
    -1.91
    
    -1.89
    POSITIVE LOGITS
    b
    2.22
    the
    2.14
    𓆜
    2.00
    le
    1.99
    d
    1.95
    un
    1.93
    g
    1.89
    ES
    1.88
    S
    1.80
    sa
    1.80
    Activations Density 0.004%

    No Known Activations