© 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. 129457
    Prev
    Next
    INDEX
    Explanations

    high pressure

    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
     blah
    -0.06
    🍭
    -0.06
     lean
    -0.06
    CFLAGS
    -0.06
     affiliated
    -0.06
     deuda
    -0.06
     puesta
    -0.06
    কন্যা
    -0.06
     Seeking
    -0.06
     tortillas
    -0.06
    POSITIVE LOGITS
     five
    0.07
     such
    0.06
     ஐந்து
    0.06
     француз
    0.06
     такой
    0.06
     Veränder
    0.06
     vijf
    0.06
     簡単
    0.06
    Тех
    0.06
     الفرنسي
    0.06
    Activations Density 0.024%

    No Known Activations