© 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. 58608
    Prev
    Next
    INDEX
    Explanations

    football positions

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

    The neuron fires on mentions of athletic field positions (e.g. flanker, central defender, left back, winger, etc.).

    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
    actéristi
    -1.34
    même
    -1.31
    Actually
    -1.21
     milioni
    -1.21
    ξ
    -1.20
     femminile
    -1.20
    鈀
    -1.18
     professionale
    -1.17
    ridescent
    -1.15
     preva
    -1.14
    POSITIVE LOGITS
     like
    1.53
     however
    1.50
     Однако
    1.48
     azonban
    1.45
     \
    1.44
     однако
    1.41
     sollte
    1.34
    主要的
    1.32
     mūsų
    1.27
     процессов
    1.27
    Activations Density 0.035%

    No Known Activations