© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120825
    Prev
    Next
    INDEX
    Explanations

    azure geo-dr cross region

    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
    Negative Logits
    ku
    -0.06
    गर
    -0.06
     Always
    -0.06
     snowboard
    -0.05
     hoffe
    -0.05
     system
    -0.05
     anderer
    -0.05
     Administración
    -0.05
    II
    -0.05
     ternary
    -0.05
    POSITIVE LOGITS
     it
    0.08
     cả
    0.07
    同時に
    0.06
     गुरूवार
    0.06
     deutsche
    0.06
     только
    0.06
     சேன
    0.06
     одновременно
    0.06
     ভারতবর্ষ
    0.06
     numai
    0.06
    Activations Density 0.001%

    No Known Activations