© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77162
    Prev
    Next
    INDEX
    Explanations

    political administrations

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

    The neuron fires on capitalized political terms—especially names of politicians, political parties, and high-office titles.

    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
     PRESIDENT
    -0.97
     Presidente
    -0.96
    President
    -0.93
    大統領
    -0.91
     president
    -0.91
     President
    -0.89
     presidential
    -0.88
     presidente
    -0.88
     politicians
    -0.88
     presidents
    -0.85
    POSITIVE LOGITS
     administration
    1.92
     Administration
    1.46
    administration
    1.37
    Administration
    1.23
     regime
    1.22
     administración
    1.17
     ADMINISTRATION
    1.13
     regering
    1.09
     administrations
    1.05
     администрации
    1.02
    Activations Density 0.027%

    No Known Activations