© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63932
    Prev
    Next
    INDEX
    Explanations

    Republican and political terms

    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
     Araújo
    -0.86
    hướng
    -0.84
     empê
    -0.79
     cumbre
    -0.78
    ườn
    -0.77
    cussions
    -0.76
    amint
    -0.76
     liderazgo
    -0.75
    ậm
    -0.75
    printf
    -0.74
    POSITIVE LOGITS
     Republicans
    1.13
    Republicans
    1.00
     Republic
    0.97
     Republican
    0.96
     republicans
    0.94
     الجمه
    0.93
     Asturias
    0.91
     republic
    0.88
     REPUBLIC
    0.86
     CNG
    0.85
    Activations Density 0.006%

    No Known Activations