© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127712
    Prev
    Next
    INDEX
    Explanations

    assembly line, conveyor

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

    The neuron strongly activates on references to manufacturing conveyance systems, such as “assembly line,” “belt conveyor,” and related conveyor terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    6
    -2.20
    2
    -2.06
    4
    -2.02
    3
    -1.95
    7
    -1.85
    5
    -1.77
    8
    -1.70
    but
    -1.68
    ⦊
    -1.67
    但我
    -1.63
    POSITIVE LOGITS
    .'
    2.02
    
    1.89
    ;"
    1.78
    ;'
    1.72
    жника
    1.70
    >
    1.67
    把手
    1.66
    嵓
    1.64
    鷓
    1.62
    :"
    1.60
    Activations Density 0.010%

    No Known Activations