© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117937
    Prev
    Next
    INDEX
    Explanations

    computer-aided manufacturing

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

    The neuron fires strongly on domain‐specific technical jargon—especially multiword manufacturing and CAD/CAM/CAE process phrases and their acronyms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Payments
    -0.82
    crimin
    -0.81
    Payments
    -0.75
    peto
    -0.72
    }\,\
    -0.71
    <0x9D>
    -0.71
     PAYMENT
    -0.70
    nings
    -0.69
    oluble
    -0.69
    PAYMENT
    -0.68
    POSITIVE LOGITS
     manufacturing
    1.09
     ASME
    1.05
     Manufacturing
    1.02
     product
    0.97
     assembly
    0.96
    Manufacturing
    0.91
    manufacturing
    0.89
     Assembly
    0.88
    Product
    0.88
    product
    0.85
    Activations Density 0.021%

    No Known Activations