© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4290
    Prev
    Next
    INDEX
    Explanations

    breakfast

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

    The neuron fires strongly on occurrences of the word “Breakfast,” effectively spotting mentions of breakfast.

    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
    하여
    0.83
    딱
    0.75
    ι
    0.74
     మీకు
    0.71
    Dieses
    0.71
    Wales
    0.70
    fø
    0.68
    ำ
    0.68
    Auction
    0.67
    Know
    0.66
    POSITIVE LOGITS
    omnia
    0.69
     mediated
    0.66
     ঝাঁপ
    0.65
     Ceg
    0.64
     Після
    0.63
     vortex
    0.62
     国家
    0.61
     不能
    0.61
     وبعد
    0.61
     強
    0.61
    Activations Density 0.002%

    No Known Activations