© 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. 84252
    Prev
    Next
    INDEX
    Explanations

    campaign aides and allies

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

    The neuron strongly activates on proper nouns and institutional names in U.S. political news stories (e.g., agency names, news outlets, campaigns, and key political figures).

    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
     “…
    -1.11
    ׇ
    -1.03
     प्रोड
    -1.01
    issão
    -0.98
     塗装
    -0.97
    illante
    -0.97
     “...
    -0.96
    macOS
    -0.94
    assioned
    -0.93
     spannende
    -0.93
    POSITIVE LOGITS
     aides
    1.13
     птиц
    0.98
     GOP
    0.93
     asiático
    0.92
    Contours
    0.85
    Giới
    0.85
     White
    0.85
     Tuesday
    0.85
    Transcripción
    0.84
     preview
    0.84
    Activations Density 0.114%

    No Known Activations