© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104912
    Prev
    Next
    INDEX
    Explanations

    wiki template markup

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

    opening double curly braces in template syntax or markup languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the double‐curly‐brace sequence “{{,” i.e. the opening of template or placeholder 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
     \
    -2.70
    ,"
    -2.55
    ’
    -2.47
    厹
    -2.44
     It
    -2.44
     When
    -2.41
     Your
    -2.36
    乆
    -2.23
     Choosing
    -2.23
     -
    -2.23
    POSITIVE LOGITS
    鲼
    2.94
    龊
    2.92
    as
    2.67
    涐
    2.66
     itſelf
    2.55
    ed
    2.50
    琲
    2.42
    😝
    2.33
    鲥
    2.31
    ⌵
    2.30
    Activations Density 0.006%

    No Known Activations