© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10693
    Prev
    Next
    INDEX
    Explanations

    actions involving play

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

    The neuron activates on words and phrases related to children’s play and kid-oriented activities or products.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    喝酒
    0.66
     алкого
    0.65
     alcoholic
    0.61
    瀘
    0.61
     alcool
    0.61
     cerveza
    0.60
     Alcoholic
    0.59
     alcohol
    0.57
     eyelashes
    0.57
    痩
    0.57
    POSITIVE LOGITS
     playground
    1.98
     playgrounds
    1.90
     Playground
    1.86
     play
    1.76
    playground
    1.70
     playtime
    1.70
     Play
    1.66
    Play
    1.63
    play
    1.59
     PLAY
    1.59
    Activations Density 0.410%

    No Known Activations