© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    column, min, goes, all, division, align, unique

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

    the neuron activates on numeric tokens—especially numbers with digits or decimal points, i.e. measurements, money amounts, statistics, 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
    use
    0.89
    و
    0.84
    a
    0.82
    ی
    0.82
    وية
    0.77
    容易
    0.73
    лни
    0.72
    難
    0.70
    ה
    0.69
    া
    0.68
    POSITIVE LOGITS
    ্স্ট
    0.95
     Leinster
    0.94
     HubSpot
    0.86
     Jackman
    0.86
    𝐿
    0.84
    ৯৫
    0.84
     hostages
    0.83
     Республи
    0.83
    れます
    0.83
     OnePlus
    0.82
    Activations Density 0.001%

    No Known Activations