© 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. 12774
    Prev
    Next
    INDEX
    Explanations

    crucial area for manufacturing

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

    The neuron fires on specialized descriptive jargon and product‐oriented terms—especially words about manufacturing precision, custom features, and technical processes.

    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
     행동
    0.77
    redir
    0.77
    Governance
    0.77
     प्रभावी
    0.75
    ُ
    0.75
     Governance
    0.74
    Intu
    0.70
    assets
    0.69
    눴
    0.68
     развед
    0.68
    POSITIVE LOGITS
     craftsmen
    1.45
     изделий
    1.41
     craftsmanship
    1.40
     manufacturing
    1.38
    工艺
    1.32
    製造
    1.30
     machining
    1.30
     craftsman
    1.29
    制造
    1.28
     изготовления
    1.27
    Activations Density 1.395%

    No Known Activations