© 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. 120298
    Prev
    Next
    INDEX
    Explanations

    commercial product

    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
     вместо
    -0.07
     foods
    -0.07
     选择
    -0.07
    Instead
    -0.07
     대신
    -0.06
     choisir
    -0.06
    까지
    -0.06
    繼續
    -0.06
     opciones
    -0.06
     instead
    -0.06
    POSITIVE LOGITS
     develop
    0.07
     copyrighted
    0.07
     similaire
    0.07
     تطوير
    0.07
     similar
    0.07
     design
    0.06
     comparable
    0.06
     developed
    0.06
     distribution
    0.06
     sell
    0.06
    Activations Density 0.001%

    No Known Activations