© 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. 10586
    Prev
    Next
    INDEX
    Explanations

    per * unit

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

    The neuron fires on numeric tokens representing large numerical measurements or values—specifically floating-point numbers (e.g. prices, rates, or counts 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
    ﺍ
    1.01
     березня
    0.98
    ताओं
    0.91
    ንሽ
    0.87
    于
    0.87
    sa
    0.86
     hoher
    0.84
    ulers
    0.84
     recited
    0.83
     ‪
    0.83
    POSITIVE LOGITS
     annum
    1.30
     capita
    1.25
    भूति
    0.89
    фект
    0.86
    信念
    0.81
    ishable
    0.78
     Excellency
    0.77
    ffected
    0.77
    क्राम
    0.77
    ّد
    0.75
    Activations Density 0.021%

    No Known Activations