© 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. 84350
    Prev
    Next
    INDEX
    Explanations

    President Obama's policies and administration

    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
     Trump
    -1.20
    Trump
    -1.20
    trump
    -0.96
     ترام
    -0.92
     trump
    -0.85
    donald
    -0.84
     músicos
    -0.78
     Ivana
    -0.78
    <0xA5>
    -0.76
     Statewide
    -0.75
    POSITIVE LOGITS
     Administration
    1.20
     administration
    1.12
     President
    1.06
    President
    1.02
     Obama
    1.01
    Administration
    0.90
     White
    0.88
    Obama
    0.87
     president
    0.86
    administration
    0.81
    Activations Density 0.076%

    No Known Activations