© 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. 8164
    Prev
    Next
    INDEX
    Explanations

    compliance and programming roles

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

    The neuron fires on mentions of “nearest airport” and its associated distance information.

    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
    ель
    0.73
    лур
    0.73
    続
    0.73
    ровка
    0.70
     continue
    0.69
    ستگی
    0.68
     Shipbuilding
    0.67
    不久
    0.67
     Continue
    0.66
     উন্নতির
    0.66
    POSITIVE LOGITS
    aard
    0.87
    deprecated
    0.81
    ⅜
    0.80
    CANCEL
    0.79
    U
    0.77
     Daff
    0.77
    cotton
    0.76
    acock
    0.76
    自定义
    0.75
     Wille
    0.75
    Activations Density 0.001%

    No Known Activations