© 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. 83251
    Prev
    Next
    INDEX
    Explanations

    socioeconomic status of families and communities

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

    The neuron detects words and phrases that denote socioeconomic status or wealth (e.g., “low-income,” “wealthy,” “poor,” “affluent,” “rich”).

    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
     wealthy
    -1.42
     impoverished
    -1.21
     affluent
    -1.16
     poverty
    -1.14
     cheaper
    -1.13
     indigent
    -1.12
     poor
    -1.11
     poorer
    -1.10
     inexpensive
    -1.02
     poorest
    -0.99
    POSITIVE LOGITS
     families
    1.36
    families
    1.12
     neighborhoods
    1.05
     households
    1.01
    BRACKET
    0.97
     bracket
    0.94
    bracket
    0.94
     communities
    0.93
     ($
    0.92
    Families
    0.89
    Activations Density 0.027%

    No Known Activations