© 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. 129467
    Prev
    Next
    INDEX
    Explanations

    lists or code snippets

    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
     ১২
    -0.07
     witty
    -0.07
     tejto
    -0.06
     Stunning
    -0.06
     této
    -0.06
     этой
    -0.06
     சம்பந்த
    -0.06
     heartwarming
    -0.06
    ина
    -0.06
    우리
    -0.06
    POSITIVE LOGITS
    Assert
    0.06
     optically
    0.06
     أو
    0.06
     natively
    0.06
     processes
    0.06
     വിശ്വാ
    0.05
    水分
    0.05
     used
    0.05
     பதில்
    0.05
    包括
    0.05
    Activations Density 0.001%

    No Known Activations