© 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. 5708
    Prev
    Next
    INDEX
    Explanations

    article + noun

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

    This neuron strongly activates on the very first content word of each new paragraph or segment, effectively marking the start of a new section.

    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
     này
    0.76
    و
    0.65
     אם
    0.64
    的最佳
    0.64
    ー
    0.64
    ([
    0.63
    вЂ
    0.62
    ו
    0.62
    [-
    0.61
    ᱱ
    0.61
    POSITIVE LOGITS
     other
    0.77
     മറ്റ്
    0.73
     અન્ય
    0.70
     consequent
    0.70
     diğer
    0.67
     অন্যান্য
    0.66
     குறிப்பாக
    0.65
     innego
    0.64
    ONE
    0.64
     innych
    0.64
    Activations Density 0.399%

    No Known Activations