© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93998
    Prev
    Next
    INDEX
    Explanations

    commercial property and retail spaces

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

    The neuron flags terminology and numbers characteristic of real‐estate listings (especially commercial property descriptors, unit/retail details, and numeric specifications).

    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
    зь
    -0.90
     HOUSING
    -0.84
    DECREF
    -0.81
    ઑ
    -0.80
    CSS
    -0.80
    采购
    -0.79
    Housing
    -0.79
     القوات
    -0.79
     salario
    -0.78
    بيت
    -0.78
    POSITIVE LOGITS
     commercial
    2.58
     office
    2.36
     retail
    2.27
     shop
    2.14
    commercial
    2.02
     Commercial
    1.98
     space
    1.91
    Commercial
    1.83
     storefront
    1.79
     offices
    1.76
    Activations Density 0.035%

    No Known Activations