© 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. 116158
    Prev
    Next
    INDEX
    Explanations

    BOOST libraries and C++ includes

    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
     at
    -0.09
     under
    -0.07
     çünkü
    -0.07
     maintains
    -0.07
     Business
    -0.07
     service
    -0.07
     only
    -0.06
     out
    -0.06
     optimizes
    -0.06
     ofrece
    -0.06
    POSITIVE LOGITS
     wraz
    0.06
     dass
    0.06
    imal
    0.06
     inscreva
    0.06
    tw
    0.05
     trước
    0.05
     Fetch
    0.05
     μαζί
    0.05
    如果是
    0.05
    রফ
    0.05
    Activations Density 0.001%

    No Known Activations