© 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. 60735
    Prev
    Next
    INDEX
    Explanations

    rent and monthly income

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

    The neuron fires on financial/accounting terms—especially rental- and property-income line items, monetary amounts, and related numeric cost/income figures.

    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
    benzo
    -0.78
     credito
    -0.77
    Ӫ
    -0.77
    loans
    -0.77
    RegistryLite
    -0.77
     endothe
    -0.76
    팔
    -0.76
    AUTH
    -0.76
     ද
    -0.75
    BUY
    -0.75
    POSITIVE LOGITS
     rent
    2.55
     rents
    2.05
     rental
    1.77
    Rent
    1.62
     Rent
    1.41
     monthly
    1.41
    rent
    1.30
    租
    1.27
    Rental
    1.19
     Rental
    1.17
    Activations Density 0.011%

    No Known Activations