© 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. 37942
    Prev
    Next
    INDEX
    Explanations

    social and political commentary

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

    This neuron fires on mentions of social or political commentary and related abstract concepts (e.g. “socially,” “social change,” “satire,” “messages,” “meanings”).

    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
    ços
    -0.95
    ForResult
    -0.92
    getItem
    -0.90
    zysty
    -0.90
    athered
    -0.87
    article
    -0.84
    ísimo
    -0.84
    стреча
    -0.84
     Deportes
    -0.83
    getResources
    -0.81
    POSITIVE LOGITS
     commentary
    2.06
     social
    2.03
     message
    1.93
     critique
    1.63
     topical
    1.60
     political
    1.52
     commentaries
    1.51
     Commentary
    1.50
     Message
    1.48
    comment
    1.48
    Activations Density 0.081%

    No Known Activations