© 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. 121075
    Prev
    Next
    INDEX
    Explanations

    code syntax and lists

    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
     необы
    -0.08
    这将
    -0.08
     десяти
    -0.07
     эти
    -0.07
    在那里
    -0.07
    これらの
    -0.06
     razie
    -0.06
    这些
    -0.06
    REFERENCES
    -0.06
     lasts
    -0.06
    POSITIVE LOGITS
     use
    0.06
    cdot
    0.06
    ,
    0.05
     পারস্প
    0.05
    ;
    0.05
     link
    0.05
     would
    0.05
     पोषण
    0.05
     আশেপাশে
    0.05
     منصوب
    0.05
    Activations Density 0.005%

    No Known Activations