© 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. 10401
    Prev
    Next
    INDEX
    Explanations

    data format conversions, recharge, medical conditions

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

    The neuron is selectively activated by numeric measurements or statistics—especially decimal numbers and percentages—embedded 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
    OLDER
    0.85
    यन
    0.79
    вому
    0.77
    ové
    0.73
     マル
    0.73
    ័យ
    0.72
    ਫ
    0.72
    ДО
    0.71
    Hình
    0.71
    ואר
    0.71
    POSITIVE LOGITS
    reviews
    0.90
    disc
    0.84
    refund
    0.80
    stocks
    0.79
    statistics
    0.77
    reflective
    0.77
    related
    0.77
    theater
    0.74
    steller
    0.73
    recognized
    0.73
    Activations Density 0.000%

    No Known Activations