© 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. 6016
    Prev
    Next
    INDEX
    Explanations

    summaries are

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

    The neuron fires on plural nouns—words ending in “s.”

    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
    들이
    0.74
    s
    0.71
    ‌هایی
    0.71
    ‌های
    0.71
    ों
    0.70
    ज
    0.68
    larla
    0.66
     ນ
    0.66
    Hig
    0.66
    setFixedHeight
    0.66
    POSITIVE LOGITS
    respective
    0.86
     respective
    0.83
     weren
    0.80
     aren
    0.76
    都很
    0.74
     various
    0.73
     commas
    0.73
    各式
    0.72
    various
    0.72
     radars
    0.71
    Activations Density 0.756%

    No Known Activations