© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 598
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron activates on tokens that form names of pharmaceutical drugs or medications.

    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_31_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
     meticulously
    0.53
    বিষ্য
    0.51
     empowers
    0.50
     hikers
    0.49
     lâng
    0.49
    🏢
    0.49
     исключительно
    0.48
    🏛
    0.48
     conscientious
    0.47
     policymakers
    0.47
    POSITIVE LOGITS
     Бу
    0.53
     Ли
    0.52
     Ла
    0.50
     Ча
    0.50
     Gambar
    0.50
     Ба
    0.48
     Jh
    0.47
     Ejemplo
    0.47
     Pseudo
    0.47
     Mà
    0.47
    Activations Density 0.201%

    No Known Activations