© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1114
    Prev
    Next
    INDEX
    Explanations

    Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite

    Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puol
    0.42
    ারক
    0.41
    伥
    0.40
    ेज
    0.38
    elseif
    0.37
    茜
    0.37
     Haq
    0.36
     CDI
    0.36
     अखिल
    0.36
    ఘ
    0.36
    POSITIVE LOGITS
     Trump
    0.97
    Trump
    0.90
    trump
    0.88
     trump
    0.81
     ट्रंप
    0.79
     Donald
    0.77
    特朗普
    0.76
    Donald
    0.72
    donald
    0.71
    ترام
    0.63
    Activations Density 0.007%

    No Known Activations