© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15735
    Prev
    Next
    INDEX
    Explanations

    numbering formats

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

    The neuron detects numerical identifiers used as structural references in documents—e.g. section/chapter/article numbers, dates, week numbers, etc.

    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
     
    0.71
     Taiwanese
    0.70
     lossless
    0.69
    т
    0.64
     parade
    0.64
     Minecraft
    0.64
     intermedi
    0.63
    вест
    0.63
     Clipper
    0.63
     Figma
    0.63
    POSITIVE LOGITS
    ඓ
    0.79
     نمبر
    0.72
     κάθε
    0.71
     ทํา
    0.69
     ช่วย
    0.68
     เดือน
    0.68
    ごとに
    0.68
    ares
    0.67
     ขึ้น
    0.67
     ฮะ
    0.67
    Activations Density 0.002%

    No Known Activations