© 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. 14233
    Prev
    Next
    INDEX
    Explanations

    cost traffic volume

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

    The neuron is detecting floating‐point numeric tokens (numbers with decimal points).

    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
    \;
    1.04
    切换
    0.86
    \,
    0.84
    供应链
    0.84
    ar
    0.82
    有什么
    0.79
    随机
    0.77
    MILLISE
    0.77
    _{\
    0.73
    一共
    0.73
    POSITIVE LOGITS
    ?!?
    0.83
     smě
    0.80
     кожи
    0.80
     emblem
    0.79
     datum
    0.78
     последнее
    0.78
     именем
    0.78
     степени
    0.77
     ответственность
    0.77
    гүй
    0.76
    Activations Density 0.000%

    No Known Activations