© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11901
    Prev
    Next
    INDEX
    Explanations

    Donald Trump presidency presidential actions

    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
     Obama
    -0.90
     Barack
    -0.86
    AKT
    -0.79
    Obama
    -0.78
     чу
    -0.75
     Rainbow
    -0.73
    ブル
    -0.71
     MAF
    -0.71
    tapa
    -0.70
     KR
    -0.69
    POSITIVE LOGITS
     deregulation
    0.97
     Goya
    0.91
    wnicy
    0.85
    Bahrain
    0.83
     Clemson
    0.82
    꿍
    0.81
     phonetic
    0.81
     CONCEP
    0.79
     Deere
    0.78
    Boca
    0.78
    Activations Density 0.026%

    No Known Activations