© 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. 11874
    Prev
    Next
    INDEX
    Explanations

    **summary table introductions**

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

    This neuron fires on lines that are repeated subject-header or “Re:” lines in an email/forum thread.

    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
     frenzy
    0.69
    🤙
    0.67
    🤘
    0.66
     जैसी
    0.65
     दिलचस्पी
    0.64
     crappy
    0.64
     firepower
    0.63
     Ztg
    0.62
     skeptic
    0.60
     booze
    0.60
    POSITIVE LOGITS
     ambayo
    0.66
    赡
    0.65
     impedir
    0.63
     එහි
    0.63
     অতএব
    0.61
    ของการ
    0.61
     জাহাঙ্গীর
    0.61
     विराम
    0.60
    ualmente
    0.59
    ებები
    0.59
    Activations Density 0.009%

    No Known Activations