© 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. 12886
    Prev
    Next
    INDEX
    Explanations

    football club names

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

    The neuron specifically detects occurrences of the uppercase abbreviation “FC.”

    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
    骘
    -2.83
    ญี่ป
    -2.75
    葑
    -2.63
    瑨
    -2.63
    ⽥
    -2.61
    马逊
    -2.55
    禩
    -2.55
     碗
    -2.53
    Conclusión
    -2.53
    畱
    -2.52
    POSITIVE LOGITS
    _
    3.34
    >
    3.20
    t
    2.95
    k
    2.94
    ar
    2.88
    if
    2.73
    id
    2.70
    )
    2.67
    o
    2.66
    -
    2.66
    Activations Density 0.011%

    No Known Activations