© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16316
    Prev
    Next
    INDEX
    Explanations

    benefit wealthy

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

    This neuron detects numeric tokens—i.e. occurrences of numbers or numerical figures in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    discussions about economic inequality, wealth distribution, and systemic financial disparities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    discussions of economics and finance, especially wealth distribution, market regulation, corporate power, and inequality.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Troubleshooting
    0.96
    Projectile
    0.96
    Notifications
    0.94
    Photography
    0.91
     اندراج
    0.89
     Enseñanza
    0.89
     Notifications
    0.89
    Hrs
    0.88
     Treatments
    0.88
     آموزشی
    0.87
    POSITIVE LOGITS
     billionaires
    1.80
     capitalists
    1.55
     billionaire
    1.54
     billions
    1.43
     oligarch
    1.43
     corporations
    1.39
     capitalist
    1.39
     trillions
    1.39
     wealthy
    1.37
     capitalism
    1.35
    Activations Density 0.730%

    No Known Activations