© 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. 120346
    Prev
    Next
    INDEX
    Explanations

    ` to ` `

    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
     использовали
    -0.07
    乃至
    -0.07
    സമ
    -0.06
     έγινε
    -0.06
     ilyen
    -0.06
    lemb
    -0.06
     использования
    -0.06
     czas
    -0.06
    之时
    -0.06
     era
    -0.06
    POSITIVE LOGITS
     عق
    0.06
    ኤ
    0.06
     তাহলে
    0.06
     семи
    0.06
     Optimization
    0.05
     then
    0.05
     tempt
    0.05
    🔽
    0.05
    ってお
    0.05
     которая
    0.05
    Activations Density 0.002%

    No Known Activations