© 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. 5359
    Prev
    Next
    INDEX
    Explanations

    addressing groups of people

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

    The neuron detects informal greeting phrases that address an audience (e.g. “Hi everyone,” “Hello all,” “Hey guys,” etc.) at the start of a message.

    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
    你不
    0.86
    你说
    0.76
     iyong
    0.75
    ست
    0.74
    ഌ
    0.73
    あなた
    0.73
    Photograph
    0.73
    lád
    0.72
    你了
    0.71
    你
    0.71
    POSITIVE LOGITS
     techs
    0.68
     and
    0.66
    s
    0.66
     libs
    0.65
     Tudo
    0.64
     Adapt
    0.63
     terbaru
    0.63
     Arkadaşlar
    0.62
     cultures
    0.61
     sectors
    0.61
    Activations Density 0.002%

    No Known Activations