© 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. 116600
    Prev
    Next
    INDEX
    Explanations

    DB connectorapples emergent readerAzure Functionswire straightenerLayout constrainttrait itselfMiss Worldlist spinnerCSS appliedjava assignment

    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
     எடுத்துக்
    -0.06
     ₹
    -0.06
     ❤️
    -0.06
     добиться
    -0.06
     ஆயிர
    -0.06
     undoubt
    -0.06
    首先
    -0.06
     ঝামে
    -0.06
     will
    -0.06
    தமிழ்
    -0.06
    POSITIVE LOGITS
     purposes
    0.09
     которая
    0.07
     Applicable
    0.06
    鏽
    0.06
     Subsequent
    0.06
    后者
    0.06
    নার্থ
    0.06
     sake
    0.06
     generation
    0.06
     всех
    0.06
    Activations Density 0.131%

    No Known Activations