© 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. 24-GEMMASCOPE-2-RES-16K
    4. 13894
    Prev
    Next
    INDEX
    Explanations

    code and web development

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

    The neuron selectively activates on proper nouns, especially geographical place names.

    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
     fün
    0.80
    ’
    0.71
     ры
    0.71
     Ры
    0.69
     Milky
    0.69
     hulp
    0.68
    rün
    0.66
     Leopold
    0.66
     ungefähr
    0.66
     dulu
    0.66
    POSITIVE LOGITS
    不知道
    0.90
    breakpoints
    0.82
    vehicles
    0.79
    原文
    0.79
     بتاريخ
    0.79
    吼
    0.77
     дода
    0.76
    covariance
    0.76
    xadmin
    0.75
    criminals
    0.75
    Activations Density 0.000%

    No Known Activations