© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22417
    Prev
    Next
    INDEX
    Explanations

    async function calls

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

    The neuron responds to the JavaScript/TypeScript keyword “async,” flagging asynchronous function declarations or expressions.

    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
    ㉓
    -1.63
     ravaged
    -1.58
     franquicia
    -1.54
     ให้
    -1.52
     horrifying
    -1.48
    </strong>
    -1.47
    ⚋
    -1.46
     zelfs
    -1.46
    大腿
    -1.46
     mediocre
    -1.45
    POSITIVE LOGITS
     gets
    2.23
     two
    1.81
     people
    1.81
     give
    1.70
     getting
    1.63
    鷓
    1.63
     takes
    1.61
     name
    1.59
    当時の
    1.55
    ༵
    1.53
    Activations Density 0.000%

    No Known Activations