© 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. 120215
    Prev
    Next
    INDEX
    Explanations

    broadcasts premiered aired on

    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
     Bundestag
    -0.07
     shawl
    -0.06
     шо
    -0.06
    ਪ
    -0.06
    kerchief
    -0.06
    Disponible
    -0.06
     акций
    -0.06
     ẞ
    -0.06
    ایل
    -0.06
    ŝ
    -0.06
    POSITIVE LOGITS
    optimal
    0.07
     darkness
    0.07
     മറ്റ
    0.06
     iba
    0.06
     would
    0.06
     Fear
    0.06
     इन
    0.06
     optimal
    0.06
     மாசுபாடு
    0.06
    view
    0.06
    Activations Density 0.010%

    No Known Activations