© 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. 117409
    Prev
    Next
    INDEX
    Explanations

    sermons and biblical texts

    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
    亮
    -0.06
     overjoyed
    -0.06
     schon
    -0.06
     project
    -0.06
     asia
    -0.06
    found
    -0.06
     পাই
    -0.06
     Impacts
    -0.06
    ⎤
    -0.05
     Troy
    -0.05
    POSITIVE LOGITS
    スピ
    0.06
     argued
    0.06
    lecture
    0.06
     выступи
    0.06
     Auschwitz
    0.06
    icone
    0.06
     क्षेत्रफल
    0.06
     addresses
    0.06
    newList
    0.06
     addr
    0.06
    Activations Density 0.019%

    No Known Activations