© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21306
    Prev
    Next
    INDEX
    Explanations

    closing delimiters followed by code syntax

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

    The neuron fires on single-quote characters used as string‐literal delimiters in code (e.g. SQL or JS strings).

    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
    In
    -4.31
    0
    -4.09
    L
    -3.89
    [
    -3.77
    Of
    -3.70
    a
    -3.48
    3
    -3.39
    \
    -3.36
    No
    -3.36
    ing
    -3.36
    POSITIVE LOGITS
    𐑂
    3.19
     белом
    3.14
    ⽬
    3.05
    樒
    3.05
    GEBUR
    3.03
    ⃤
    3.03
    瘜
    2.94
    榈
    2.91
    䊏
    2.91
    
    2.89
    Activations Density 0.001%

    No Known Activations