© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99129
    Prev
    Next
    INDEX
    Explanations

    defect inspection for surfaces

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

    The neuron strongly activates on technical discussion of “inspection” (especially in the context of image- or pattern-based defect detection).

    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
    ﹄
    -0.80
    εί
    -0.78
    chân
    -0.74
    YAxis
    -0.73
     vecchia
    -0.72
    chsel
    -0.72
    ศ
    -0.72
     یخ
    -0.71
    льский
    -0.70
    guous
    -0.69
    POSITIVE LOGITS
     inspection
    1.88
     inspecting
    1.47
     inspectors
    1.47
     inspections
    1.45
     inspect
    1.33
     Inspection
    1.33
     Inspect
    1.29
     inspected
    1.28
    inspection
    1.28
    Inspection
    1.24
    Activations Density 0.092%

    No Known Activations