© 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. 10-GEMMASCOPE-RES-131K
    7. 103060
    Prev
    Next
    INDEX
    Explanations

    mortgage and housing market

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

    The neuron strongly activates on real-estate–related proper names and jargon (e.g. brokers, MLS, title companies, mortgage lenders, REALTOR®, property terms).

    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
    pherals
    -1.23
     وغ
    -1.13
    sufficient
    -1.13
    聽
    -1.13
    ）
    -1.12
     десять
    -1.10
     dévelo
    -1.08
    ков
    -1.07
    ización
    -1.06
    ごめん
    -1.05
    POSITIVE LOGITS
    כך
    1.36
    摑
    1.29
     réglementation
    1.23
     both
    1.20
     Both
    1.20
    三百
    1.20
    calips
    1.19
     tradizionale
    1.18
    🪆
    1.16
    marzo
    1.14
    Activations Density 0.093%

    No Known Activations