© 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. 70727
    Prev
    Next
    INDEX
    Explanations

    sports actions and objects

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

    The neuron fires on words that describe gaining or handling possession in sports—especially catching, grabbing, hauling in, or similar ball/puck control actions.

    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
    而且
    -1.33
    chalten
    -1.28
     kolei
    -1.26
     to
    -1.24
    ₤
    -1.23
     sentire
    -1.19
    新的
    -1.18
     的
    -1.17
     penser
    -1.17
    wiście
    -1.16
    POSITIVE LOGITS
     our
    1.80
     when
    1.66
     then
    1.42
     esperamos
    1.41
    いかが
    1.23
    行きます
    1.23
     queremos
    1.18
     many
    1.17
     as
    1.16
     this
    1.15
    Activations Density 0.024%

    No Known Activations