© 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. 56748
    Prev
    Next
    INDEX
    Explanations

    politicians and outcomes

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

    The neuron detects mentions of major political figures’ names (especially candidates) in the text.

    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
     Inſ
    -0.94
     Diſ
    -0.90
    élev
    -0.89
     electing
    -0.86
    botas
    -0.85
    tuar
    -0.84
    ˒
    -0.82
    ೣ
    -0.81
    ContextMenu
    -0.81
    tifiable
    -0.80
    POSITIVE LOGITS
     appeal
    1.23
     received
    1.03
     visited
    1.01
     appeals
    0.93
     visit
    0.92
     wins
    0.90
     benefit
    0.87
     alien
    0.86
     promise
    0.85
     опи
    0.85
    Activations Density 0.043%

    No Known Activations