© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102905
    Prev
    Next
    INDEX
    Explanations

    White House presidential activities

    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
     Statewide
    -0.90
     billboards
    -0.90
     statewide
    -0.89
    裁判
    -0.80
     Spices
    -0.79
     legislators
    -0.79
     Wohnungen
    -0.78
     Hints
    -0.78
    вила
    -0.78
    łeś
    -0.77
    POSITIVE LOGITS
     White
    2.16
    White
    1.66
     presidential
    1.53
     Presidential
    1.52
     Secret
    1.45
     President
    1.35
     WHITE
    1.27
    ホワイト
    1.27
    Presidential
    1.14
     president
    1.10
    Activations Density 0.041%

    No Known Activations