© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on verbs (especially contentful action words, including “-ing” forms and past participles).

    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
    ôme
    0.78
    anat
    0.76
     innovations
    0.75
     Bs
    0.75
    o
    0.73
    an
    0.73
    íes
    0.71
     thân
    0.71
    arı
    0.70
     ở
    0.70
    POSITIVE LOGITS
    رو
    0.80
    TRAVEL
    0.77
     کھلا
    0.76
     fielded
    0.76
    CHEMICAL
    0.76
    ए
    0.76
    CHILD
    0.76
    神奈川
    0.73
    ما
    0.72
    とか
    0.72
    Activations Density 0.000%

    No Known Activations