© 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. 117723
    Prev
    Next
    INDEX
    Explanations

    diagrams and figures

    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
     dessen
    -0.07
     aritm
    -0.07
     leisurely
    -0.06
     whisk
    -0.06
    мін
    -0.06
     argumentative
    -0.06
    menin
    -0.05
     whose
    -0.05
     couv
    -0.05
     pemas
    -0.05
    POSITIVE LOGITS
     참고
    0.07
     ምንም
    0.07
     কাজকর্ম
    0.06
     американ
    0.06
     plastic
    0.06
     উক্ত
    0.06
     aluminum
    0.06
     spoilers
    0.06
     what
    0.05
     과거
    0.05
    Activations Density 0.001%

    No Known Activations