© 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. 22-GEMMASCOPE-RES-131K
    7. 128141
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on mentions of “cookie” (especially in code contexts like document.cookie or Cookie functions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    javascript cookie operations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     \
    -1.25
    sl
    -1.18
     and
    -1.10
     or
    -1.09
     a
    -1.08
     with
    -1.02
     ворота
    -1.02
     /
    -1.01
     wyjątk
    -1.00
    滔
    -1.00
    POSITIVE LOGITS
     饼
    1.15
    弹窗
    1.14
    也會
    1.14
    Их
    1.10
     位置
    1.09
    Вариант
    1.09
     américains
    1.08
    Вопрос
    1.08
     penyimpanan
    1.08
    èles
    1.06
    Activations Density 0.010%

    No Known Activations