© 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. 10033
    Prev
    Next
    INDEX
    Explanations

    square kilometers / miles

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

    The neuron strongly activates on numeric tokens containing decimal‐point measurements (i.e. floating‐point numbers).

    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
     I
    0.80
    <0x80>
    0.71
    0.71
    我
    0.70
    рати
    0.68
    اد
    0.68
    0
    0.68
     DM
    0.66
    стки
    0.66
    icon
    0.66
    POSITIVE LOGITS
     sukces
    0.90
     ۋ
    0.86
    笾
    0.86
     फ़
    0.84
     карты
    0.84
    ição
    0.84
     বৎ
    0.84
     patham
    0.83
     olas
    0.83
    োগ্য
    0.82
    Activations Density 0.002%

    No Known Activations