© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3973
    Prev
    Next
    INDEX
    Explanations

    distance in miles or kilometers

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

    The neuron activates strongly on numeric measurement tokens (e.g. distances and other numeric values).

    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
     слегка
    0.80
     cumplir
    0.74
     necesitaba
    0.69
    嘭
    0.69
     largos
    0.67
    🍨
    0.66
     humedad
    0.66
     lágrimas
    0.66
     PYTHONPATH
    0.64
     fumes
    0.64
    POSITIVE LOGITS
    го
    0.61
    総合
    0.60
    ة
    0.60
    по
    0.59
    zai
    0.59
    í
    0.59
    奥
    0.59
    وی
    0.57
    and
    0.57
     socialist
    0.57
    Activations Density 0.016%

    No Known Activations