© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    as an introduction

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

    The neuron is looking for floating‐point numeric tokens (numbers containing decimal points).

    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
    嫂
    0.77
    çay
    0.74
    èi
    0.74
    entraî
    0.73
    af
    0.73
    赛季
    0.72
    ુંદર
    0.71
    确实
    0.70
    alors
    0.70
    俬
    0.70
    POSITIVE LOGITS
     будущее
    0.80
    𝚐
    0.78
    вые
    0.75
     выполнение
    0.74
     общий
    0.73
    ী
    0.72
     ἡ
    0.71
    ी
    0.71
    зи
    0.70
    раб
    0.70
    Activations Density 0.002%

    No Known Activations