© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5703
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude and thanks

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

    The neuron activates on expressions of gratitude or thanks.

    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_31_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
    ֒
    0.55
    ":[
    0.55
     invertible
    0.55
     disturbing
    0.52
    ocell
    0.52
     예측
    0.52
     الشيطان
    0.50
     progn
    0.50
     мони
    0.50
    띤
    0.49
    POSITIVE LOGITS
     thank
    3.41
     THANK
    3.34
     gratitude
    3.28
     thanked
    3.28
     thanking
    3.28
     Thank
    3.20
    感谢
    3.16
    THANK
    3.16
    感謝
    3.11
    thank
    3.05
    Activations Density 0.608%

    No Known Activations