© 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. 7651
    Prev
    Next
    INDEX
    Explanations

    C++ includes

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

    The neuron fires on the “<” token in C/C++ #include statements, especially when including standard headers with angle brackets.

    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
    ‘
    -1.89
    ಱ
    -1.86
     beliebtesten
    -1.86
     订单
    -1.84
    が多く
    -1.82
     metodología
    -1.79
     estadía
    -1.77
    了几
    -1.73
    rii
    -1.73
    이고
    -1.73
    POSITIVE LOGITS
     it
    2.23
     However
    2.22
    However
    1.77
    際には
    1.73
    鏵
    1.70
    鴣
    1.66
     鐵
    1.64
     They
    1.64
    3
    1.63
     may
    1.59
    Activations Density 0.031%

    No Known Activations