© 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. 31-GEMMASCOPE-2-RES-16K
    4. 10605
    Prev
    Next
    INDEX
    Explanations

    following 'in' and 'increases'

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

    The neuron detects decimal numerals or floating-point measurement values in a text.

    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
    ocrates
    0.70
    Bacteria
    0.68
    Khi
    0.65
    bacteria
    0.64
     측정
    0.63
    oldi
    0.61
    OCR
    0.61
    😇
    0.61
     khuẩn
    0.60
     kimia
    0.60
    POSITIVE LOGITS
     second
    0.84
     második
    0.73
     fourth
    0.66
     naïve
    0.64
     городских
    0.64
     première
    0.63
     Enhanced
    0.62
     Second
    0.61
     второго
    0.60
     local
    0.60
    Activations Density 0.243%

    No Known Activations