© 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. 5817
    Prev
    Next
    INDEX
    Explanations

    happy emojis

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

    The neuron strongly fires on tokens representing laughter or amusement (e.g. “lol,” “haha,” “🙂”), i.e. informal, emotive interjections.

    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
    ToDO
    0.86
     izgrad
    0.85
     costruzione
    0.81
     adanya
    0.80
    ЛЬ
    0.80
    ENTITY
    0.80
     쪽
    0.80
     கட்டப்பட்டது
    0.80
     році
    0.78
     відбу
    0.78
    POSITIVE LOGITS
    ています
    1.22
    mert
    1.00
    🙃
    0.98
    🙂
    0.96
     Toxicology
    0.95
    😅
    0.95
     Mers
    0.93
    😂
    0.91
     simul
    0.86
    रहे
    0.86
    Activations Density 0.010%

    No Known Activations