© 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. 12396
    Prev
    Next
    INDEX
    Explanations

    return the result

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

    The neuron strongly activates on spans containing quantitative data—numbers, measurements, prices, or other metric/statistical details.

    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
    認識
    0.74
    入
    0.66
    getC
    0.66
    p
    0.66
    計算
    0.65
    ților
    0.65
    احة
    0.65
    糖尿
    0.64
    ס
    0.64
    人口
    0.64
    POSITIVE LOGITS
    ming
    0.81
     ETFs
    0.79
    clusively
    0.78
    बर्ट
    0.77
    artment
    0.76
    িতে
    0.76
    meng
    0.76
    leyball
    0.75
    brevi
    0.75
     voluntad
    0.75
    Activations Density 0.000%

    No Known Activations