© 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. 129156
    Prev
    Next
    INDEX
    Explanations

    African presidents

    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
     versión
    -0.07
     versione
    -0.06
     חלק
    -0.06
     بخشی
    -0.06
     данным
    -0.06
    mainly
    -0.06
     المستقيم
    -0.06
     نسخة
    -0.06
     Olson
    -0.06
    docs
    -0.06
    POSITIVE LOGITS
     compact
    0.06
     już
    0.06
     inaugur
    0.06
     appla
    0.06
    શ
    0.06
     eerie
    0.06
     unut
    0.05
     unites
    0.05
     will
    0.05
     already
    0.05
    Activations Density 0.001%

    No Known Activations