© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70022
    Prev
    Next
    INDEX
    Explanations

    quotation marks and surrounding code

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

    The neuron fires on quotation marks used as string delimiters (single or double quotes) in code or markup.

    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
     möjlighet
    -2.23
    There
    -2.22
    حياته
    -2.13
     其
    -2.00
    Almost
    -1.99
    飄
    -1.98
     ikkje
    -1.95
     spise
    -1.91
    这是什么
    -1.91
    Some
    -1.91
    POSITIVE LOGITS
    {
    2.64
     we
    2.52
    翃
    2.48
    を始め
    2.31
    튿
    2.28
    --
    2.20
    I
    2.17
    in
    2.17
    er
    2.14
    for
    2.13
    Activations Density 0.001%

    No Known Activations