© 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. 128304
    Prev
    Next
    INDEX
    Explanations

    set/var assignment

    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
     grâce
    -0.07
     возвра
    -0.07
     díky
    -0.07
     gracias
    -0.07
     في
    -0.06
     technological
    -0.06
     вследствие
    -0.06
     grazie
    -0.06
     বাঙালী
    -0.06
     nell
    -0.06
    POSITIVE LOGITS
     tales
    0.07
     two
    0.06
     most
    0.06
    ;
    0.06
     not
    0.06
     also
    0.06
     مثال
    0.06
     almost
    0.06
     just
    0.06
     criminal
    0.05
    Activations Density 0.001%

    No Known Activations