© 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. 108907
    Prev
    Next
    INDEX
    Explanations

    Democrats and Republicans

    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
    מוד
    -0.82
     saites
    -0.82
    ***/
    -0.79
    getInt
    -0.77
    )();
    -0.76
    curly
    -0.76
    coders
    -0.75
     peuple
    -0.74
    )");
    -0.74
    िए
    -0.74
    POSITIVE LOGITS
     Democrats
    4.06
     Republicans
    3.91
    Democrats
    3.06
     Republican
    3.06
    Republicans
    2.95
     Democratic
    2.72
     Democrat
    2.70
    Republican
    2.33
     democrats
    2.31
     republicans
    2.28
    Activations Density 0.086%

    No Known Activations