© 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. 10984
    Prev
    Next
    INDEX
    Explanations

    communist and authoritarian political systems

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

    The neuron strongly activates on terms referring to political authority or regimes—words about control, governments, communist or authoritarian systems, and named states.

    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
     franchisee
    0.58
    intermedi
    0.58
     SSL
    0.56
    SSL
    0.55
     Refund
    0.55
     reembol
    0.55
     Mediation
    0.55
    <iframe>
    0.55
     Kelsey
    0.55
     negociación
    0.55
    POSITIVE LOGITS
     totalitarian
    2.00
     dictatorship
    1.80
     dictator
    1.73
     dictators
    1.68
     Stalin
    1.62
     Communist
    1.49
     communist
    1.48
     Communism
    1.47
     tyrannical
    1.45
     authoritarian
    1.45
    Activations Density 0.274%

    No Known Activations