© 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. 129298
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
    قق
    -0.06
    :
    -0.06
    కర్
    -0.06
     রাস্তার
    -0.06
    কার
    -0.05
    ণার
    -0.05
     spesial
    -0.05
     özel
    -0.05
     कला
    -0.05
     created
    -0.05
    POSITIVE LOGITS
     दोनों
    0.07
     these
    0.07
     этих
    0.07
    这两个
    0.07
     помога
    0.07
    這些
    0.07
     இரண்டு
    0.07
     جنوب
    0.07
    兩個
    0.06
     तीन
    0.06
    Activations Density 0.019%

    No Known Activations