© 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. 119352
    Prev
    Next
    INDEX
    Explanations

    SQL 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
     这个
    -0.06
    ,.
    -0.06
     hacen
    -0.06
    Even
    -0.06
     contexto
    -0.06
     如果
    -0.06
     最
    -0.06
     在
    -0.06
     reliance
    -0.06
     มั้ย
    -0.06
    POSITIVE LOGITS
     लागि
    0.06
     চারি
    0.06
    🤗
    0.06
    ★
    0.06
     cinque
    0.06
     пять
    0.06
     integrantes
    0.06
    🤐
    0.06
    😀
    0.06
     fifteen
    0.06
    Activations Density 0.030%

    No Known Activations