© 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. 22-GEMMASCOPE-RES-131K
    7. 129369
    Prev
    Next
    INDEX
    Explanations

    Republican and conservative politics

    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_22/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
     getP
    -1.13
     msglen
    -1.05
    Democratic
    -1.05
     ItemType
    -1.03
     ImageButton
    -0.97
    (",");
    -0.96
    oregon
    -0.95
     yPos
    -0.94
     Ngb
    -0.94
     minera
    -0.94
    POSITIVE LOGITS
     Conservatives
    1.45
     conservative
    1.30
     conservatives
    1.29
     Conservative
    1.28
    Conservative
    1.16
     righ
    1.16
    Tämä
    1.12
     conservatism
    1.08
     white
    1.05
     bất
    1.00
    Activations Density 0.249%

    No Known Activations