© 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. 92724
    Prev
    Next
    INDEX
    Explanations

    Donald Trump candidate president

    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
     carport
    -0.96
    Assassin
    -0.80
    Netflix
    -0.77
    Beans
    -0.77
     Fulham
    -0.76
     Boucher
    -0.75
    Pico
    -0.74
     Scholz
    -0.73
    достатки
    -0.73
     Guevara
    -0.73
    POSITIVE LOGITS
     Donald
    1.43
     candidate
    1.39
     Trump
    1.30
     Candidate
    1.19
    candidate
    1.15
    Donald
    1.12
     CANDIDATE
    1.12
     donald
    1.09
     candidacy
    1.08
    Candidate
    1.07
    Activations Density 0.044%

    No Known Activations