© 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. 116094
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and inequalities

    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
    cccc
    -0.06
     áp
    -0.06
     audio
    -0.06
     பாஜக
    -0.06
     সিরিজে
    -0.06
    线的
    -0.06
    không
    -0.06
    audio
    -0.06
     कैसे
    -0.06
     being
    -0.06
    POSITIVE LOGITS
     plans
    0.06
     specialties
    0.06
     believing
    0.06
    srand
    0.06
     Gelegenheit
    0.05
     few
    0.05
    叻
    0.05
     खूब
    0.05
    说了
    0.05
     then
    0.05
    Activations Density 0.012%

    No Known Activations