© 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. 10096
    Prev
    Next
    INDEX
    Explanations

    Bollinger, Fuse, author, OBJECT

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

    The neuron is detecting email‐style reply/forward headers and subject‐line fragments (e.g. “Re:”, repeated subject tokens, uppercase abbreviations).

    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
    ↵
    0.73
    お願いします
    0.68
     chiedere
    0.68
    เหตุ
    0.66
     odio
    0.61
    あなた
    0.61
     nihil
    0.60
     −/−
    0.59
    そこ
    0.59
     dodge
    0.59
    POSITIVE LOGITS
    样的
    0.71
     televised
    0.71
    დის
    0.71
    দয়
    0.70
     bosom
    0.69
    джи
    0.67
    ladı
    0.65
    जेंसी
    0.64
    planar
    0.64
     सितारों
    0.64
    Activations Density 0.013%

    No Known Activations