© 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. 19887
    Prev
    Next
    INDEX
    Explanations

    web requests

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

    This neuron detects mentions of URL‐fetching APIs and network request calls (e.g. urllib.request, urlopen, URLSession).

    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
    O
    -1.74
    And
    -1.70
    ができます
    -1.59
    怍
    -1.50
     secreta
    -1.49
     egens
    -1.48
    ocrats
    -1.47
     hidrá
    -1.45
    According
    -1.45
     priser
    -1.43
    POSITIVE LOGITS
    认可
    1.58
    ровал
    1.49
     "
    1.44
     composición
    1.44
    ."
    1.43
    に関して
    1.37
    ႐
    1.32
    тера
    1.31
     felicidad
    1.30
    </sup>
    1.29
    Activations Density 0.019%

    No Known Activations