© 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. 119032
    Prev
    Next
    INDEX
    Explanations

    nationalities or origins

    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
     umano
    -0.06
     universal
    -0.06
    driven
    -0.06
     cephal
    -0.06
     countries
    -0.05
    ↓↓
    -0.05
     Tropical
    -0.05
     coupé
    -0.05
     global
    -0.05
     humano
    -0.05
    POSITIVE LOGITS
     Flood
    0.07
     manhã
    0.07
     quien
    0.06
    废水
    0.06
     düzey
    0.06
     অংশে
    0.06
     perfetto
    0.06
     自転車
    0.06
    lık
    0.06
    ellia
    0.06
    Activations Density 0.012%

    No Known Activations