© 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. 13951
    Prev
    Next
    INDEX
    Explanations

    not divide substitute register yaml

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

    The neuron strongly activates on the preposition “from.”

    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
    ੋਂ
    0.73
    та
    0.73
    <0xDB>
    0.68
     jā
    0.67
    θαν
    0.67
     Ам
    0.67
     λό
    0.66
     絶対
    0.66
     ospiti
    0.66
    rę
    0.65
    POSITIVE LOGITS
    밭
    0.79
     pueblos
    0.75
    жный
    0.75
    ITIONAL
    0.72
     válida
    0.72
     blades
    0.72
    ชัน
    0.71
     crumb
    0.71
    Addr
    0.70
    基础上
    0.70
    Activations Density 0.000%

    No Known Activations