© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66474
    Prev
    Next
    INDEX
    Explanations

    code keywords and document beginnings

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

    The neuron strongly activates on references to cookies (e.g. accessing `Cookie`, `document.cookie`, or calling a “getCookie” function).

    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
     if
    -1.63
     nếu
    -0.96
    if
    -0.92
     если
    -0.90
    ifdef
    -0.87
     اگر
    -0.79
    IfNeeded
    -0.79
    ciamo
    -0.79
    usnya
    -0.78
     elér
    -0.77
    POSITIVE LOGITS
    reiras
    0.89
    oney
    0.81
    ㄹ
    0.80
    accountId
    0.79
     eléctricas
    0.78
     Freitag
    0.76
    珐
    0.76
    ”?
    0.74
    )».
    0.74
     will
    0.74
    Activations Density 0.021%

    No Known Activations