© 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. 22-GEMMASCOPE-RES-131K
    7. 67357
    Prev
    Next
    INDEX
    Explanations

    AJAX requests

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

    The neuron strongly activates on JavaScript/Ajax code terms—especially XMLHttpRequest, xhr, new, and related function calls—i.e. it’s looking for JS Ajax/XHR code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.47
     Gesund
    -1.23
     newborn
    -1.05
    での
    -1.04
    interess
    -0.98
     Banken
    -0.98
     flesta
    -0.97
     universitaire
    -0.97
    alatan
    -0.95
     Перейти
    -0.94
    POSITIVE LOGITS
    WillAppear
    1.27
    ulipas
    1.18
    DeclareMath
    1.16
    関連リンク
    1.12
    他对
    1.11
    accessible
    1.09
    rors
    1.09
    ワクワク
    1.09
    ælde
    1.08
    挥手
    1.06
    Activations Density 0.007%

    No Known Activations