© 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. 31-GEMMASCOPE-2-RES-16K
    4. 10361
    Prev
    Next
    INDEX
    Explanations

    brief and impactful moments

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

    The neuron detects numeric expressions of time spans (e.g., “days,” “3-day,” “years”) indicating durations.

    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
     years
    0.85
     decades
    0.79
     দীর্ঘদিন
    0.78
     বহুদিন
    0.77
     months
    0.77
     오래
    0.75
    多年
    0.73
     몇
    0.72
     hours
    0.71
     YEARS
    0.71
    POSITIVE LOGITS
     consecutivos
    0.91
     inactivity
    0.80
     uninterrupted
    0.80
     nonstop
    0.76
     geleden
    0.75
     captivity
    0.74
     intense
    0.73
    樣子
    0.73
    captivity
    0.71
     existence
    0.70
    Activations Density 0.272%

    No Known Activations