© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9531
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by words

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

    The neuron is triggered by numeric expressions—quantities, dosages, prices, and other number tokens.

    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_31_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
     Ú
    0.61
     clay
    0.61
     OEM
    0.60
     oasis
    0.60
     EPL
    0.59
     Guides
    0.57
    榆
    0.55
     diamond
    0.55
     dot
    0.54
     ctrl
    0.54
    POSITIVE LOGITS
    Insufficient
    0.64
    Gracias
    0.58
    Thanks
    0.56
     الجيش
    0.55
     カード
    0.54
    ﹂
    0.53
     manifestazione
    0.53
     desapar
    0.52
    下跌
    0.52
     desaparecer
    0.51
    Activations Density 0.114%

    No Known Activations