© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    current time, today

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

    This neuron fires on meaningful content words (nouns, verbs, adjectives, etc.) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    text fragments that are part of longer, structured documents or database entries, particularly where content continues across sections.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to history and cultural traditions framed over time, especially contrasts between past and present and mentions of long-standing practices across societies.

    oai_token-act-pair · gpt-5Triggered 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
     sebelumnya
    0.66
     preth
    0.66
     previously
    0.63
     Previously
    0.62
     wcześniej
    0.62
    ান্তি
    0.62
    previously
    0.62
     précédemment
    0.61
     préal
    0.59
     ஏற்கனவே
    0.59
    POSITIVE LOGITS
     today
    3.53
    today
    3.22
     todays
    3.20
     heutigen
    3.06
     Today
    3.02
    Today
    3.00
    今天的
    2.98
     сегодня
    2.95
     oggi
    2.94
     오늘
    2.89
    Activations Density 0.834%

    No Known Activations