© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    ajax requests and calls

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

    This neuron activates on occurrences of the substring “ajax,” for example in script‐src URLs or identifiers containing “ajax.”

    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
     It
    -3.31
    ).
    -2.98
     But
    -2.80
    箩
    -2.28
     that
    -2.22
     like
    -2.20
     แต่
    -2.19
    大腿
    -2.19
    .’
    -2.17
    también
    -2.16
    POSITIVE LOGITS
    鴞
    2.50
     itſelf
    2.50
    感じ
    2.38
    樉
    2.34
     élas
    2.33
    1
    2.31
     couver
    2.30
    牁
    2.30
     teknologi
    2.25
     kursi
    2.23
    Activations Density 0.005%

    No Known Activations