© 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. 5971
    Prev
    Next
    INDEX
    Explanations

    quite / pretty modifying adjectives

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

    The neuron responds to degree words and intensifiers—tokens like “quite,” “lot,” “much,” “some,” “number,” etc., that signal magnitude or emphasis.

    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
     questões
    0.98
     спраши
    0.96
    questions
    0.95
    ्स
    0.93
    ד
    0.88
    scholar
    0.87
     лишь
    0.86
    scorer
    0.86
    ຮູ້
    0.84
     рынке
    0.84
    POSITIVE LOGITS
    து
    0.97
    呦
    0.94
    DD
    0.93
    ters
    0.92
    <table>
    0.92
    ী
    0.89
    缁
    0.87
    I
    0.86
     wee
    0.86
     tremble
    0.85
    Activations Density 0.112%

    No Known Activations