© 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. 7430
    Prev
    Next
    INDEX
    Explanations

    The neuron detects formal spoken‐address salutations, notably instances of “ladies and gentlemen.”

    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
    ные
    1.01
    𝑜
    0.82
    ный
    0.80
    ных
    0.78
    ной
    0.78
    ského
    0.78
    으로
    0.78
    ્સ
    0.77
    ഋ
    0.77
    🫢
    0.77
    POSITIVE LOGITS
    儘
    0.76
    ing
    0.73
     éta
    0.72
     preparations
    0.69
     bhaj
    0.68
     patience
    0.67
     Princes
    0.66
    いたしました
    0.66
     bookings
    0.65
     barbecue
    0.64
    Activations Density 0.098%

    No Known Activations