© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    years or future targets

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

    The neuron is tuned to pick up numeric expressions—quantities, statistics, dates, monetary amounts, percentages, etc.

    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
     Almost
    0.63
     récent
    0.62
     Week
    0.61
    ící
    0.59
     Allí
    0.59
     ออนไลน์
    0.59
     Nisan
    0.58
    t
    0.58
    stas
    0.57
     Http
    0.57
    POSITIVE LOGITS
    三年
    1.21
    五年
    1.20
    明年
    1.09
    今後
    1.02
    未來
    1.02
    未来
    0.95
    目標
    0.95
    两年
    0.90
    十年
    0.90
     আগামী
    0.89
    Activations Density 0.176%

    No Known Activations