© 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. 2078
    Prev
    Next
    INDEX
    Explanations

    industrial estate or park

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

    The neuron strongly responds to numeric tokens (sequences of digits) such as street numbers, postal codes, years, and other numbers in the text.

    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
    [][]
    -0.82
     Residents
    -0.79
     pubblico
    -0.79
    Quat
    -0.79
     residents
    -0.78
     rozwiązania
    -0.78
     dostępne
    -0.77
    흔
    -0.77
     overuse
    -0.77
     ausgestattet
    -0.77
    POSITIVE LOGITS
     industrial
    2.31
    industrial
    2.02
     Industrial
    1.99
    Industrial
    1.77
     INDUSTRIAL
    1.70
     Gewerbe
    1.57
     warehouse
    1.52
     industria
    1.29
     industriale
    1.28
     industriales
    1.24
    Activations Density 0.044%

    No Known Activations