© 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. 50005
    Prev
    Next
    INDEX
    Explanations

    dictatorships and regimes

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

    This neuron primarily picks out violent or militarized geopolitical contexts—mentions of conflict, attacks, dictators, and the countries or leaders involved.

    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
    塑料
    -0.80
     Schles
    -0.79
     refund
    -0.76
     Projectile
    -0.75
     Alkohol
    -0.74
    ört
    -0.73
     Manns
    -0.73
     война
    -0.71
    ónde
    -0.71
    Refund
    -0.71
    POSITIVE LOGITS
     regime
    3.19
     regimes
    2.69
    regime
    2.31
     Regime
    2.30
     режима
    1.99
     dictator
    1.95
     régimen
    1.92
     Dict
    1.84
     dictators
    1.78
     dictatorship
    1.75
    Activations Density 0.047%

    No Known Activations