© 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. 119337
    Prev
    Next
    INDEX
    Explanations

    location context

    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
    機会
    -0.07
    Algorithm
    -0.07
     nedeni
    -0.06
     bố
    -0.06
     disebabkan
    -0.06
    数は
    -0.06
    数が
    -0.06
     diagrama
    -0.06
    ফাজ
    -0.06
     solver
    -0.06
    POSITIVE LOGITS
    (?)
    0.06
     했습니다
    0.06
    /
    0.06
     høy
    0.06
    hey
    0.06
     inviol
    0.06
     높은
    0.06
    ध्यक्ष
    0.06
    ใน
    0.05
    -/
    0.05
    Activations Density 0.041%

    No Known Activations