© 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. 14325
    Prev
    Next
    INDEX
    Explanations

    design and creation

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

    The neuron activates strongly on jargon and terms related to corporate/business operations and strategy.

    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
     достовер
    0.82
     erhältlich
    0.76
     thrill
    0.70
     occurrences
    0.70
     elated
    0.69
    倘
    0.68
     eligible
    0.68
    ゎ
    0.67
     আশংকা
    0.66
     peruse
    0.66
    POSITIVE LOGITS
     desain
    0.97
     设计
    0.95
    变革
    0.95
     디자인
    0.94
    设计
    0.91
     构建
    0.89
     tasarım
    0.88
     设置
    0.88
     bâtiments
    0.88
     설계
    0.88
    Activations Density 0.190%

    No Known Activations