© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116434
    Prev
    Next
    INDEX
    Explanations

    international relations, foreign affairs, and government officials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     アメリカ
    -0.08
     американ
    -0.08
     여름
    -0.07
     amerikanischen
    -0.07
     amerikan
    -0.07
     summer
    -0.07
     uneasy
    -0.07
    мерикан
    -0.07
    夏天
    -0.07
     미국
    -0.07
    POSITIVE LOGITS
    after
    0.06
    来店
    0.05
     quickly
    0.05
     Ubud
    0.05
     bribery
    0.05
     ষড়যন্ত্র
    0.05
     прид
    0.05
    ToServer
    0.05
    CFT
    0.05
     Bogor
    0.05
    Activations Density 0.001%

    No Known Activations