© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119142
    Prev
    Next
    INDEX
    Explanations

    appellant or district

    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
     of
    -0.08
     are
    -0.07
     without
    -0.07
     ohne
    -0.07
     in
    -0.07
     отличаются
    -0.07
    Software
    -0.06
     использу
    -0.06
    प्रभाव
    -0.06
    ตั้งแต่
    -0.06
    POSITIVE LOGITS
    :
    0.08
    an
    0.06
     yakni
    0.06
     ہمارا
    0.06
    ]:
    0.06
     unthinkable
    0.06
     what
    0.06
     usual
    0.05
     considerable
    0.05
     অসুবিধা
    0.05
    Activations Density 0.010%

    No Known Activations