© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10623
    Prev
    Next
    INDEX
    Explanations

    Japanese numerals and years

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

    The neuron selectively fires on numeric tokens—especially years, dates, and large numeric values.

    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_31_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
    <unused20>
    0.77
     توانید
    0.76
    atória
    0.75
    <unused1>
    0.73
     ब्लॉग
    0.72
     poate
    0.71
     arxiv
    0.71
     கொரோனா
    0.71
    <unused19>
    0.70
     आरआर
    0.70
    POSITIVE LOGITS
     ১৯৭
    2.03
     ১৯৮
    2.02
     ১৯৯
    1.74
     ১৯৬
    1.71
     ۱۹
    1.64
     १९
    1.51
    昭和
    1.45
    ۱۹
    1.45
     ১৯৬৫
    1.45
    ১৯
    1.34
    Activations Density 0.432%

    No Known Activations