© 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. 128739
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     Então
    -0.07
     Entonces
    -0.07
     Uno
    -0.07
    はその
    -0.07
     τότε
    -0.06
     entonces
    -0.06
     agat
    -0.06
     Тогда
    -0.06
     Кроме
    -0.06
    有一种
    -0.06
    POSITIVE LOGITS
     how
    0.06
    arquivo
    0.06
    هاي
    0.06
    geving
    0.06
     እድ
    0.05
    ۝
    0.05
     যেভাবে
    0.05
     bilo
    0.05
     मसाज
    0.05
     debate
    0.05
    Activations Density 0.004%

    No Known Activations