© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8351
    Prev
    Next
    INDEX
    Explanations

    specific words followed by punctuation

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

    The neuron detects floating‐point numbers (numerical tokens containing a decimal point).

    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
     eet
    0.77
    **
    0.71
    {
    0.70
    凝
    0.70
    Weighted
    0.68
    他也
    0.67
    size
    0.67
    ää
    0.66
    så
    0.66
    Greet
    0.66
    POSITIVE LOGITS
     INSPIRE
    0.79
     บวก
    0.77
    ੭
    0.77
     nello
    0.76
    あなたが
    0.75
    ност
    0.73
     reais
    0.73
    座標
    0.73
    ร
    0.73
    िया
    0.72
    Activations Density 0.000%

    No Known Activations