© 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. 85720
    Prev
    Next
    INDEX
    Explanations

    code punctuation and special characters

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

    The neuron fires on the ampersand (“&”) operator (i.e. address‐of/reference usage) in 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
     також
    -1.71
    %;">
    -1.70
    欽
    -1.67
    %",
    -1.66
    %',
    -1.59
     senhora
    -1.54
    骓
    -1.53
    焄
    -1.53
     také
    -1.48
     irmã
    -1.41
    POSITIVE LOGITS
     that
    2.13
    0
    1.68
     ofrecen
    1.63
     señaló
    1.57
     mania
    1.50
    liferation
    1.48
     udě
    1.48
     indicó
    1.48
    dată
    1.48
    锝
    1.43
    Activations Density 0.001%

    No Known Activations