© 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. 104287
    Prev
    Next
    INDEX
    Explanations

    key-value pair

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

    The neuron fires on JavaScript code that parses and iterates over document.cookie (splitting by “;” and looping through cookie entries).

    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
    nyata
    -1.05
    felizmente
    -0.93
     to
    -0.89
    なんですよ
    -0.87
    лита
    -0.86
    libur
    -0.86
    verbs
    -0.85
    ؤلاء
    -0.85
    phylo
    -0.84
     启动
    -0.84
    POSITIVE LOGITS
    Pair
    1.23
    Both
    1.19
     both
    1.16
     दोनों
    1.16
    both
    1.15
     Both
    1.13
    兩
    1.11
     beiden
    1.10
     beide
    1.09
     entrambi
    1.04
    Activations Density 0.031%

    No Known Activations