© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9744
    Prev
    Next
    INDEX
    Explanations

    creation

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

    The neuron specializes in spotting numeric values and quantitative measurements (numbers and associated units or counts).

    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
    IfExists
    0.70
    が無い
    0.68
    whatever
    0.68
    ﭥ
    0.68
    LastError
    0.67
    isNaN
    0.65
    ()!=
    0.65
    ไม่
    0.64
    숫
    0.64
     نشده
    0.63
    POSITIVE LOGITS
     créer
    0.81
     create
    0.76
     sebuah
    0.73
    创建一个
    0.73
     isang
    0.73
     creare
    0.72
     crear
    0.70
     creando
    0.70
     deux
    0.69
     नया
    0.69
    Activations Density 0.290%

    No Known Activations