© 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. 10518
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on named entities or proper names (e.g. people, places, branded terms, titles).

    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
    ado
    0.71
    ти
    0.71
    ل
    0.70
    ًا
    0.65
     वीं
    0.64
    icos
    0.64
    स्ता
    0.63
    であろう
    0.63
    iasco
    0.62
    ुट
    0.61
    POSITIVE LOGITS
     Việc
    0.81
     ratione
    0.67
     Tổ
    0.66
    ₁(
    0.63
    `;
    0.62
    ちなみに
    0.62
     Многие
    0.62
     Χ
    0.61
     chợ
    0.61
     Extensive
    0.61
    Activations Density 1.224%

    No Known Activations