© 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. 80724
    Prev
    Next
    INDEX
    Explanations

    asynchronous operations

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

    The neuron activates on tokens that are programming API calls or method names (e.g. XMLHttpRequest, openConnection, GetSize, NewGuid).

    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
    that
    -2.30
    䉴
    -2.14
     selben
    -2.03
     μαύ
    -1.97
    房产
    -1.94
     beschreiben
    -1.84
    我
    -1.80
    责编
    -1.79
     Einzelnen
    -1.78
     بدون
    -1.77
    POSITIVE LOGITS
    \
    3.06
    '
    2.94
    猡
    2.34
    鹮
    2.25
    Ꮀ
    2.20
    肏
    2.19
    .
    2.16
    ⇹
    2.09
    銦
    2.03
    已经在
    1.98
    Activations Density 0.001%

    No Known Activations