© 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. 120852
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    primarily
    -0.06
     sogenannten
    -0.06
    귿
    -0.06
     socalled
    -0.06
    noc
    -0.06
     sogenannte
    -0.06
    মাস
    -0.06
     Encu
    -0.06
    వారి
    -0.05
     基于
    -0.05
    POSITIVE LOGITS
    .
    0.08
    ;
    0.08
    ；
    0.07
    ):
    0.06
    .;
    0.06
    ),
    0.06
    ？
    0.06
    可
    0.06
     mogao
    0.06
     posso
    0.06
    Activations Density 0.005%

    No Known Activations