© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2534
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on expressions of thanks and appreciation, i.e. polite “thank you” or similar gratitude phrases.

    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
     képes
    0.59
     повин
    0.56
     nữ
    0.54
    きましょう
    0.54
    依法
    0.52
     unlawfully
    0.51
     представлена
    0.51
    뿐
    0.51
    шают
    0.50
     здания
    0.50
    POSITIVE LOGITS
    我又
    0.91
    我现在
    0.86
    我已经
    0.83
     avevo
    0.80
     teşekkür
    0.80
     meine
    0.79
     Thanks
    0.78
    我也
    0.78
     আমি
    0.77
     제가
    0.77
    Activations Density 0.291%

    No Known Activations