© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65303
    Prev
    Next
    INDEX
    Explanations

    football organizations and entities

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

    The neuron strongly activates on occurrences of the capitalized word “Football.”

    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
    \
    -3.52
     Which
    -3.45
    Here
    -2.84
    Now
    -2.83
    を
    -2.78
    It
    -2.75
    に
    -2.73
    With
    -2.61
    In
    -2.61
    Alongside
    -2.58
    POSITIVE LOGITS
    ჱ
    3.14
    逦
    3.02
    鸶
    2.89
    鼷
    2.86
    雠
    2.73
    襌
    2.70
    衚
    2.69
     tył
    2.66
     unsere
    2.63
    猡
    2.63
    Activations Density 0.010%

    No Known Activations