© 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. 128299
    Prev
    Next
    INDEX
    Explanations

    orientalism and exoticism

    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
    ometrical
    -0.07
     সংগ্রামের
    -0.06
     podia
    -0.06
     hidrógeno
    -0.06
     опти
    -0.06
    支撑
    -0.06
     दास
    -0.06
     encuentro
    -0.06
     Madhya
    -0.06
    στημα
    -0.06
    POSITIVE LOGITS
     LONDON
    0.06
    select
    0.06
    如果我们
    0.06
     EUROPE
    0.06
    SELECT
    0.06
     seleccione
    0.06
     çıktı
    0.06
     parties
    0.06
    ฏ
    0.06
     తెలిపారు
    0.06
    Activations Density 0.001%

    No Known Activations