© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    modeling, derivatives, monopsony, curious

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

    The neuron primarily activates on numeric tokens containing decimal points (floating-point numbers).

    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
    anço
    0.88
     emberek
    0.87
    adera
    0.87
    ﭜ
    0.86
    alnya
    0.85
     ধরন
    0.84
     형태
    0.84
     laureate
    0.84
    ческая
    0.84
     жовт
    0.83
    POSITIVE LOGITS
    t
    0.77
    清晰
    0.71
    ناه
    0.70
    יה
    0.69
    ماع
    0.67
    屯
    0.67
    تما
    0.66
    ຮ
    0.65
    to
    0.64
    tu
    0.64
    Activations Density 0.002%

    No Known Activations