© 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. 129288
    Prev
    Next
    INDEX
    Explanations

    annoyed at politicians

    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
     incluso
    -0.06
     reluctance
    -0.06
     sending
    -0.06
    sending
    -0.06
     ආරක්ෂ
    -0.06
    kaz
    -0.06
     termasuk
    -0.06
     भाषाओं
    -0.06
     uomo
    -0.06
     probablemente
    -0.06
    POSITIVE LOGITS
    别人的
    0.06
    addEventListener
    0.06
    ొప్ప
    0.06
     unicode
    0.06
     INTEREST
    0.06
    anders
    0.06
     Вайлд
    0.06
    倒入
    0.05
     broken
    0.05
     Filipino
    0.05
    Activations Density 0.067%

    No Known Activations