© 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. 32518
    Prev
    Next
    INDEX
    Explanations

    election and voting topics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ヴィトン
    -0.80
    ACIAS
    -0.77
     installs
    -0.75
    тє
    -0.75
     outrage
    -0.73
     Pon
    -0.73
    箪
    -0.72
     aws
    -0.71
     ADR
    -0.71
    fram
    -0.70
    POSITIVE LOGITS
     precinct
    1.28
     voters
    1.05
     partisan
    0.98
     Precinct
    0.90
    Rp
    0.81
     precincts
    0.80
     challenges
    0.77
     anticipo
    0.77
     Democrats
    0.76
     Election
    0.74
    Activations Density 0.015%

    No Known Activations