© 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. 78775
    Prev
    Next
    INDEX
    Explanations

    US political parties and elections

    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
     Democrat
    -1.20
    紅茶
    -1.04
     BJP
    -1.01
     democracies
    -0.96
    archiviato
    -0.93
     Democrats
    -0.92
     eventuell
    -0.91
     Democratic
    -0.90
    IBOutlet
    -0.90
     flavorful
    -0.89
    POSITIVE LOGITS
     Party
    1.55
     party
    1.17
     presidential
    1.00
     illustratie
    0.96
    Party
    0.95
    controlled
    0.91
     inspección
    0.90
     vorige
    0.88
    cuses
    0.86
     leaders
    0.85
    Activations Density 0.031%

    No Known Activations