© 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. 117345
    Prev
    Next
    INDEX
    Explanations

    leading order

    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
    Like
    -0.07
     Like
    -0.07
    next
    -0.07
     начале
    -0.07
     wahrscheinlich
    -0.06
    的第一
    -0.06
    δια
    -0.06
     یورپی
    -0.06
     ০৯
    -0.06
    getFirst
    -0.06
    POSITIVE LOGITS
     family
    0.06
     for
    0.06
     Family
    0.06
    Family
    0.06
     între
    0.06
    REQUIRE
    0.06
    家族
    0.06
    generation
    0.06
     Blanca
    0.05
     refuse
    0.05
    Activations Density 0.001%

    No Known Activations