© 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. 117713
    Prev
    Next
    INDEX
    Explanations

    qualities of positive traits

    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
     certain
    -0.07
     we
    -0.07
     পণ্য
    -0.06
     sebelumnya
    -0.06
     the
    -0.06
    abstraction
    -0.06
     tertentu
    -0.06
     can
    -0.06
     fasc
    -0.06
     heretofore
    -0.06
    POSITIVE LOGITS
     Consultez
    0.07
     выбора
    0.06
     involving
    0.06
     选择
    0.06
     numerosos
    0.06
    實
    0.06
     onların
    0.06
     resulting
    0.06
     schwier
    0.06
    다른
    0.06
    Activations Density 0.012%

    No Known Activations