© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7426
    Prev
    Next
    INDEX
    Explanations

    breakfast

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

    The neuron fires on explicit references to mealtimes or times of day (e.g. “breakfast,” “morning,” clock times like “3 AM,” “afternoon tea,” etc.).

    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
    cology
    0.84
     dosing
    0.81
     thiab
    0.81
    l
    0.81
    7
    0.81
     listrik
    0.79
     Laboratories
    0.78
     dosimetry
    0.78
    4
    0.77
     şi
    0.76
    POSITIVE LOGITS
    朝
    0.97
     Breakfast
    0.90
     मॉर्निंग
    0.85
    モーニング
    0.84
    ただ
    0.84
     Brunch
    0.82
     очеред
    0.82
     manhã
    0.82
    Breakfast
    0.81
    selfobj
    0.81
    Activations Density 0.053%

    No Known Activations