© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47794
    Prev
    Next
    INDEX
    Explanations

    industrial processes and structures

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

    The neuron detects numeric values and quantitative measurements (e.g., dates, amounts, units, and percentages).

    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
     matrícula
    -0.94
     industriales
    -0.87
    Indust
    -0.84
    Factories
    -0.82
     industrial
    -0.81
    istungs
    -0.81
    Provenance
    -0.80
     factories
    -0.79
    factories
    -0.79
     Bản
    -0.78
    POSITIVE LOGITS
     receiving
    1.03
     Receiving
    1.00
     silos
    0.97
     process
    0.95
     Buildings
    0.90
    Lines
    0.89
     Main
    0.88
     Meal
    0.87
    Main
    0.86
     weigh
    0.84
    Activations Density 0.034%

    No Known Activations