© 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. 128095
    Prev
    Next
    INDEX
    Explanations

    properties and methods

    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
     acerca
    -0.06
    起到
    -0.06
     בשנת
    -0.06
     charred
    -0.06
    ซึ่ง
    -0.06
     फ़ोन
    -0.06
     saved
    -0.06
     egyéb
    -0.06
    にご
    -0.06
     Austral
    -0.05
    POSITIVE LOGITS
     as
    0.08
     at
    0.07
     on
    0.07
     যথ
    0.06
     in
    0.06
     terus
    0.06
    IST
    0.06
     setengah
    0.06
    At
    0.06
     Even
    0.06
    Activations Density 0.099%

    No Known Activations