© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    family and life events

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

    The neuron fires strongly on the “nomnom” eating‐sound hashtag (and similar “nom nom” tokens), i.e. on the onomatopoetic marker for tasty food.

    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
     Tháng
    0.63
    ภ
    0.61
     Đường
    0.59
    ሐ
    0.59
    <0x04>
    0.59
    РИ
    0.59
    Allister
    0.59
    Û
    0.59
    ,#
    0.58
    А
    0.58
    POSITIVE LOGITS
     perv
    0.61
     time
    0.61
     virtuel
    0.59
     virtual
    0.58
    time
    0.57
     attire
    0.57
     hindsight
    0.56
     pleasure
    0.55
     वैल्यू
    0.55
     grassroots
    0.55
    Activations Density 0.000%

    No Known Activations