© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8334
    Prev
    Next
    INDEX
    Explanations

    regex characters and delimiters

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

    The neuron is detecting forward‐slash characters used as separators in navigation paths or breadcrumbs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    편
    0.57
    SEPT
    0.57
    坌
    0.57
     berken
    0.55
     pointer
    0.54
     сти
    0.54
    上品
    0.54
    बलेट
    0.53
    styl
    0.52
    ヨーク
    0.52
    POSITIVE LOGITS
     missing
    0.55
     Missing
    0.55
     نوفمبر
    0.55
     ත
    0.54
     নিচ্ছে
    0.54
     ဗ
    0.54
    EMY
    0.54
     Owned
    0.52
     Source
    0.51
     نوٹ
    0.51
    Activations Density 0.001%

    No Known Activations