© 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. 58370
    Prev
    Next
    INDEX
    Explanations

    U.S. Senators and Governors

    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
     dey
    -0.89
    rosin
    -0.86
     laman
    -0.86
     RECIPES
    -0.84
     CONSE
    -0.82
    艳
    -0.81
    lakes
    -0.81
     crown
    -0.81
     SHOES
    -0.81
     valide
    -0.80
    POSITIVE LOGITS
     Northam
    0.88
     gubernatorial
    0.87
     Democrat
    0.82
     ша
    0.81
     Kyiv
    0.80
     legislator
    0.80
     Califor
    0.79
    QF
    0.78
     Durban
    0.78
    やすい
    0.77
    Activations Density 0.106%

    No Known Activations