© 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. 116359
    Prev
    Next
    INDEX
    Explanations

    risk factors assessment

    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
     About
    -0.07
     Noting
    -0.06
     বিনিয়োগ
    -0.06
     acompan
    -0.06
    Having
    -0.06
    certificates
    -0.06
     Pasta
    -0.05
    About
    -0.05
     busiest
    -0.05
    ಮನ
    -0.05
    POSITIVE LOGITS
     জিজ্ঞাস
    0.06
    个人
    0.06
     predisposition
    0.06
     persönlichen
    0.06
     personal
    0.06
    个人的
    0.06
     প্রশ্নের
    0.06
     McKin
    0.06
    uição
    0.06
     asks
    0.06
    Activations Density 0.048%

    No Known Activations