© 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. 13747
    Prev
    Next
    INDEX
    Explanations

    adverbs of manner, sync, matrix

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

    the neuron strongly activates on numeric tokens—especially decimal numbers—wherever they appear.

    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
    in
    0.80
    o
    0.79
     Workshop
    0.78
    it
    0.76
     is
    0.75
     ist
    0.73
     esse
    0.73
     nelle
    0.72
    だ
    0.71
    es
    0.71
    POSITIVE LOGITS
    ượt
    0.80
     detoxification
    0.78
    𝙛
    0.77
    𝑑
    0.76
     phosphatidyl
    0.75
     persecution
    0.75
    𝙧
    0.74
    𝙙
    0.74
     teeming
    0.73
     transforming
    0.73
    Activations Density 0.001%

    No Known Activations