© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    "will teach" or "Disclaimer"

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

    This neuron is highly activated by discourse-marker tokens (e.g. “because,” “considering,” “aware,” semicolons, list numerals), i.e. words and punctuation that signal transitions or clause connections.

    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
     logarithm
    0.74
     ৬
    0.73
    <?,
    0.73
     または
    0.72
     cantor
    0.72
    0
    0.71
    ৩
    0.71
     ':'
    0.70
    %");
    0.70
     distX
    0.70
    POSITIVE LOGITS
    សម្រាប់ការ
    0.78
    विण्यासाठी
    0.76
    valuation
    0.75
     couture
    0.75
    णार्‍या
    0.74
     සඳහා
    0.72
    ތ
    0.72
    providers
    0.71
    នៅក្នុង
    0.71
    देख
    0.70
    Activations Density 0.001%

    No Known Activations