© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130616
    Prev
    Next
    INDEX
    Explanations

    template tags and code syntax

    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
    ולי
    -0.07
     Abstand
    -0.06
     somewhat
    -0.06
    🥣
    -0.06
     so
    -0.06
    thebibliography
    -0.06
    有一些
    -0.06
    🥘
    -0.06
     TV
    -0.06
     základ
    -0.06
    POSITIVE LOGITS
     obesidad
    0.07
    before
    0.07
     oba
    0.06
    度に
    0.06
    する場合は
    0.06
     BEFORE
    0.06
     ف
    0.06
     maupun
    0.06
     abnormality
    0.06
    噪音
    0.06
    Activations Density 0.018%

    No Known Activations