© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    years and software

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

    The neuron activates on numeric tokens—especially multi-digit numbers such as years, statistics, and other numeric measurements.

    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
    🫶
    1.89
     covid
    1.88
     🥰
    1.84
     pandemic
    1.80
    🥰
    1.80
     COVID
    1.79
     Covid
    1.79
    🤍
    1.77
    🥲
    1.73
    🥹
    1.68
    POSITIVE LOGITS
     ২০১৬
    1.74
     ২০১৫
    1.59
     ২০১৭
    1.46
     ২০১৪
    1.44
     २०१
    1.44
    http
    1.42
     Huffington
    1.31
     नोटबंदी
    1.31
     xrange
    1.28
    goo
    1.27
    Activations Density 3.130%

    No Known Activations