© 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. 119709
    Prev
    Next
    INDEX
    Explanations

    our focus, our mission

    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
     awesome
    -0.06
     interesting
    -0.06
     больш
    -0.06
     tricky
    -0.06
     males
    -0.06
     nifty
    -0.06
     seven
    -0.06
     pozn
    -0.06
    ressant
    -0.06
     ciekaw
    -0.06
    POSITIVE LOGITS
     your
    0.07
     그렇게
    0.07
     või
    0.06
     propose
    0.06
     någon
    0.06
     предлагает
    0.06
     عندك
    0.06
     nějak
    0.06
     proposes
    0.06
     accordingly
    0.06
    Activations Density 0.008%

    No Known Activations