© 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. 23709
    Prev
    Next
    INDEX
    Explanations

    Foucault surveillance discipline

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

    The neuron fires on mentions of the novel title “Foucault’s Pendulum” (and closely related title fragments).

    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
    conia
    -0.73
     McConnell
    -0.70
     maids
    -0.70
    ▄
    -0.70
     chung
    -0.69
     аппети
    -0.68
     হ
    -0.67
     сыром
    -0.67
    atever
    -0.66
    ffed
    -0.66
    POSITIVE LOGITS
     Foucault
    1.90
    Fou
    1.78
     Discipline
    1.30
     Fou
    1.30
    Discipline
    1.16
     surveillance
    1.15
     disciplinary
    1.11
     surve
    1.09
     Discipl
    1.05
     السلطة
    1.04
    Activations Density 0.015%

    No Known Activations