© 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. 37890
    Prev
    Next
    INDEX
    Explanations

    socioeconomic class

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

    The neuron responds to words naming or describing a person’s social identity or socioeconomic background (e.g. class or privilege markers).

    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
    ísimas
    -0.97
    謚
    -0.87
    $_.
    -0.85
    ۟
    -0.85
    
    -0.85
     RADIUS
    -0.85
    vature
    -0.84
     Genealogy
    -0.83
    ísi
    -0.82
    izmu
    -0.81
    POSITIVE LOGITS
     middle
    5.19
    middle
    4.03
    Middle
    3.23
     upper
    2.97
     Middle
    2.95
    MIDDLE
    2.86
     MIDDLE
    2.73
    upper
    2.25
     affluent
    2.14
     Upper
    1.97
    Activations Density 0.061%

    No Known Activations