© 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. 116515
    Prev
    Next
    INDEX
    Explanations

    introduction or section header

    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
    rendo
    -0.06
     বিস্ফোর
    -0.06
     बु
    -0.06
     ഏത
    -0.06
     hız
    -0.06
     LA
    -0.05
     menu
    -0.05
     announced
    -0.05
    arg
    -0.05
     twos
    -0.05
    POSITIVE LOGITS
     cotid
    0.06
     particulier
    0.06
     nhá
    0.06
     কারণে
    0.06
     takeover
    0.06
    INTRODUCTION
    0.06
     ofert
    0.06
     فِي
    0.06
     PostgreSQL
    0.06
     jeweil
    0.06
    Activations Density 0.001%

    No Known Activations