© 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. 8147
    Prev
    Next
    INDEX
    Explanations

    features, applications, or technical details

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

    This neuron activates most strongly on words (or word‐like tokens) ending in a “y” sound (i.e. tokens whose final character is “y”).

    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
     Chihuahua
    0.76
    چال
    0.73
     stomp
    0.71
    沙漠
    0.71
     Cherokee
    0.71
     mellem
    0.71
    ے
    0.71
    经过
    0.69
     قرآن
    0.69
     EARLY
    0.69
    POSITIVE LOGITS
     здравоохра
    0.85
    да
    0.79
     испыта
    0.75
    лы
    0.74
     widowed
    0.72
    язы
    0.71
    ̶
    0.71
     নেন
    0.69
     экс
    0.69
     обновления
    0.67
    Activations Density 0.002%

    No Known Activations