© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    fractions or divisions

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

    The neuron fires on tokens that signal instructional or advisory language—i.e. the “to”-infinitive and other markers of recommendations and how-to directions.

    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
    new
    0.68
    ur
    0.66
    Y
    0.65
    4
    0.63
    U
    0.62
    ウ
    0.62
    https
    0.61
     雨
    0.61
    pppp
    0.60
    川
    0.59
    POSITIVE LOGITS
    ्लाई
    0.62
    িকল্প
    0.61
     ничек
    0.61
    DBGPRINT
    0.60
     Cumm
    0.60
     Moser
    0.60
     روی
    0.59
    䢌
    0.59
     এক্ষেত্রে
    0.59
     decompression
    0.59
    Activations Density 0.032%

    No Known Activations