© 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. 10333
    Prev
    Next
    INDEX
    Explanations

    fucking

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

    The main thing this neuron does is detect swear words or expletive intensifiers used for emphasis or strong emotion.

    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
     Orrell
    0.77
     prototypical
    0.72
     ise
    0.68
    蔼
    0.68
    很多
    0.68
    旎
    0.67
    很好的
    0.66
     Kays
    0.66
     Biswas
    0.66
     formidable
    0.66
    POSITIVE LOGITS
    Мо
    1.10
    М
    1.09
    Ма
    1.03
    Мі
    1.02
    А
    1.01
    Р
    0.94
    Х
    0.92
    Й
    0.91
    На
    0.87
    Т
    0.85
    Activations Density 0.008%

    No Known Activations