© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8632
    Prev
    Next
    INDEX
    Explanations

    wealth inequality and business leaders

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

    The neuron fires on named entities—especially proper names of people and organizations (and associated dates or titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    Equations
    0.61
     lactation
    0.59
    Zombie
    0.59
    魉
    0.59
    Teacher
    0.58
     Teacher
    0.58
    LException
    0.57
     Peltier
    0.57
     teacher
    0.57
    ={{
    0.56
    POSITIVE LOGITS
     billionaire
    2.33
     billionaires
    2.20
     tycoon
    1.96
     philanthropist
    1.81
     businessman
    1.76
     philanthrop
    1.67
     businessmen
    1.66
     entrepreneur
    1.62
     imprend
    1.59
     wealthy
    1.59
    Activations Density 0.629%

    No Known Activations