© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10778
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to action words in their present‐participle (–ing) form.

    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_24_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
    )$.
    0.98
    ד
    0.98
    )$,
    0.88
    ‌ای
    0.79
     кстати
    0.79
    চ্ছেন
    0.78
    ดย
    0.77
    ‌تر
    0.77
    ]=
    0.76
    착
    0.76
    POSITIVE LOGITS
    ع
    0.86
    ness
    0.77
     oneself
    0.74
     responders
    0.73
     σημ
    0.72
    iality
    0.71
    تور
    0.71
    他
    0.71
     #{
    0.71
    ians
    0.70
    Activations Density 0.556%

    No Known Activations