© 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. 4412
    Prev
    Next
    INDEX
    Explanations

    Nazi Germany and WWII

    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
     гармо
    -0.80
     Powder
    -0.71
    celo
    -0.70
     substance
    -0.68
    bini
    -0.68
    Powder
    -0.68
    powder
    -0.66
    Weapon
    -0.66
    cdon
    -0.65
    genommen
    -0.64
    POSITIVE LOGITS
     Eich
    1.70
     Nazi
    1.06
     nazis
    1.00
     Barbie
    0.99
     Adolf
    0.95
     Nazis
    0.94
     Browning
    0.94
     SS
    0.94
     nazi
    0.89
    Barbie
    0.88
    Activations Density 0.048%

    No Known Activations