© 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. 72739
    Prev
    Next
    INDEX
    Explanations

    UEFA Euro or Champions League

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

    The neuron primarily activates on the occurrence of the acronym “UEFA.”

    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
    ).
    -2.81
     o
    -2.69
    ",
    -2.67
    ".
    -2.61
    ?
    -2.53
    ;
    -2.52
    \
    -2.45
    w
    -2.41
    y
    -2.34
     {
    -2.33
    POSITIVE LOGITS
    鹀
    2.33
    浤
    2.28
    肏
    2.27
    ܜ
    2.27
    螢幕
    2.19
    ឵
    2.17
    銛
    2.14
     forêts
    2.14
    "];
    2.13
    ㈯
    2.13
    Activations Density 0.001%

    No Known Activations