© 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. 129052
    Prev
    Next
    INDEX
    Explanations

    Testing and research

    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
     ఏర్ప
    -0.06
     الوقت
    -0.06
     bagging
    -0.06
    ストーリー
    -0.06
     templates
    -0.06
    積分
    -0.06
    Reminder
    -0.06
     вами
    -0.06
     erstellen
    -0.06
     template
    -0.06
    POSITIVE LOGITS
     Research
    0.07
    Tested
    0.06
     trust
    0.06
    Research
    0.06
     tested
    0.06
    一行
    0.06
     trusting
    0.06
     research
    0.06
     reassuring
    0.06
     verified
    0.06
    Activations Density 0.034%

    No Known Activations