© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13687
    Prev
    Next
    INDEX
    Explanations

    code blocks

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

    The neuron specifically picks up on regex‐style code tokens—backslashes, quotes, brackets, and other metacharacters used in regular expressions.

    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_24_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
     corrid
    0.74
    𝘻
    0.70
     patric
    0.68
     Schaus
    0.67
    टी
    0.66
     ं
    0.66
     identically
    0.66
     pike
    0.64
     Zahn
    0.64
     diversas
    0.64
    POSITIVE LOGITS
    ...*/
    1.10
    This
    0.95
    ཝ
    0.91
     Этот
    0.90
    這個
    0.89
    এই
    0.86
     라는
    0.84
    Een
    0.83
    इस
    0.83
    यह
    0.83
    Activations Density 0.154%

    No Known Activations