© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16066
    Prev
    Next
    INDEX
    Explanations

    explanation of code or instructions

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

    This neuron fires on numeric tokens—years, dates, measurements, or other numbers in the 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_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
     Yellowstone
    0.86
    學生
    0.86
     aantal
    0.85
     Перейти
    0.85
     Диа
    0.84
     другой
    0.82
     ง
    0.82
    Спољашње
    0.81
     Mohan
    0.81
     столь
    0.81
    POSITIVE LOGITS
    デニム
    0.74
    تمل
    0.71
     concreta
    0.70
    iffo
    0.70
     networks
    0.68
    ನ್ನ
    0.67
    icits
    0.67
    ARE
    0.66
    ことになる
    0.64
    腴
    0.64
    Activations Density 0.001%

    No Known Activations