© 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. 73969
    Prev
    Next
    INDEX
    Explanations

    template syntax constructs

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

    This neuron detects code‐ or template‐syntax delimiters—tokens like “[”, “{%”, “{{”, “#”, etc., that signal non–natural‐language markup or code.

    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
     of
    -2.36
    槩
    -2.36
    ～。
    -2.34
    があります
    -2.27
    お得
    -2.22
     間取り
    -2.22
    𞤢
    -2.20
     専門
    -2.20
    ・・。
    -2.17
    自身的
    -2.06
    POSITIVE LOGITS
    ſelf
    3.14
    颯
    2.53
     Öffnen
    2.44
    ?}
    2.34
     ‘’
    2.30
    к
    2.27
     Перейти
    2.23
     ......
    2.23
     μην
    2.23
    ҿ
    2.20
    Activations Density 0.083%

    No Known Activations