© 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. 10672
    Prev
    Next
    INDEX
    Explanations

    insert

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

    That neuron fires on numeric data—tokens representing counts, percentages, measurements, or other quantitative/statistical figures.

    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
    ল
    0.70
     personnels
    0.65
    paysys
    0.65
     extenso
    0.64
     bearers
    0.63
     flesh
    0.63
     标准
    0.62
     quarters
    0.61
     拉
    0.61
    ദീ
    0.60
    POSITIVE LOGITS
    didn
    0.84
    FG
    0.80
    n
    0.77
    doesn
    0.73
    EP
    0.72
    CH
    0.71
     FOB
    0.71
    Baba
    0.70
     सीआरपीएफ
    0.70
    ığımız
    0.69
    Activations Density 0.001%

    No Known Activations