© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending sentences

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

    The neuron selectively activates on English past-tense or past-participle words ending in “-ed.”

    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
    processed
    0.52
    utilizzo
    0.51
     информация
    0.50
    떄
    0.47
    ಚಿತ
    0.46
     када
    0.46
    本次
    0.46
    воро
    0.45
    צא
    0.45
    нение
    0.45
    POSITIVE LOGITS
    。”
    0.75
    ۔
    0.73
    。
    0.69
    。"
    0.66
     But
    0.65
    ！
    0.64
    ."
    0.64
    ™.
    0.64
    !?
    0.64
    ។
    0.64
    Activations Density 0.000%

    No Known Activations