© 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. 8601
    Prev
    Next
    INDEX
    Explanations

    Manchester United

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

    The neuron is specialized to detect mentions of the football club Manchester United (including its abbreviations and related proper nouns such as “Old Trafford”).

    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
    </h3>
    -1.70
    huriyet
    -1.67
    นี้
    -1.62
    they
    -1.59
    We
    -1.59
     came
    -1.58
    Sebelumnya
    -1.56
     If
    -1.55
     After
    -1.54
    责任编辑
    -1.54
    POSITIVE LOGITS
    出了一
    1.76
     continúas
    1.70
     acorde
    1.62
    いくつかの
    1.61
    撂
    1.55
     столько
    1.53
    푃
    1.50
     ferv
    1.48
    很是
    1.47
     ทุก
    1.46
    Activations Density 0.013%

    No Known Activations