© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62412
    Prev
    Next
    INDEX
    Explanations

    Ministerial actions and party policy

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

    The neuron strongly activates on formal mentions of government ministers and their official titles (e.g. “the Minister of Trade,” “the Minister of Agriculture,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ваясь
    -0.88
    Général
    -0.81
     EEUU
    -0.79
    𝗈
    -0.77
    sslich
    -0.75
    ↘
    -0.75
    ᾷ
    -0.75
    美国
    -0.74
    〜
    -0.74
    欧洲
    -0.73
    POSITIVE LOGITS
     Labor
    1.02
     party
    0.96
     ministerial
    0.92
     ministers
    0.92
     Party
    0.91
     List
    0.88
     парла
    0.85
     policy
    0.84
     Minister
    0.82
    party
    0.81
    Activations Density 0.013%

    No Known Activations