© 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. 34-GEMMASCOPE-RES-131K
    7. 77912
    Prev
    Next
    INDEX
    Explanations

    American football

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

    The neuron strongly activates on mentions of gridiron/American football (e.g. league names like NFL/CFL and position terms such as “wide receiver” or “tight end”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Funcs
    -0.76
    タクシー
    -0.71
    ]#
    -0.69
    alain
    -0.68
    global
    -0.67
    下一篇
    -0.67
    帰って
    -0.66
    感じで
    -0.65
    リゾート
    -0.65
    Specifically
    -0.65
    POSITIVE LOGITS
     football
    4.22
    football
    3.42
    Football
    3.30
     Football
    3.14
    🏈
    3.00
     NFL
    2.73
    NFL
    2.58
     FOOTBALL
    2.55
     footballers
    2.22
     footballer
    2.16
    Activations Density 0.108%

    No Known Activations