© 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. 8596
    Prev
    Next
    INDEX
    Explanations

    creative and unique design

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

    The neuron spotlights corporate-brochure style keywords—job titles, service and product descriptors, and other business jargon.

    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
     recid
    0.83
     welfare
    0.81
     misconduct
    0.75
     devlet
    0.75
    👮
    0.73
     விசார
    0.72
     Verteid
    0.71
     ICRC
    0.70
     보호
    0.70
    🆚
    0.69
    POSITIVE LOGITS
     decorative
    2.09
    decorative
    1.79
     decorating
    1.76
     dekor
    1.75
     Decorative
    1.74
     embell
    1.73
    装饰
    1.67
     декора
    1.66
     decoration
    1.63
     decoração
    1.63
    Activations Density 2.372%

    No Known Activations