© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9492
    Prev
    Next
    INDEX
    Explanations

    production and manufacturing

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

    The neuron fires on words and phrases that denote industrial production or manufacturing activities.

    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
    im
    1.37
    o
    1.24
    c
    1.24
    ož
    1.19
    m
    1.18
    p
    1.11
    ტ
    1.09
    d
    1.09
    etrain
    1.08
    های
    1.07
    POSITIVE LOGITS
    生产
    1.87
     Production
    1.75
     Producing
    1.65
     생산
    1.58
    生產
    1.57
     PRODUCTION
    1.55
    Production
    1.55
     production
    1.52
     manufacture
    1.52
     productions
    1.52
    Activations Density 0.530%

    No Known Activations