© 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. 127981
    Prev
    Next
    INDEX
    Explanations

    until recently

    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
     initially
    -0.08
     Initially
    -0.07
    最初は
    -0.06
    最初
    -0.06
     autrefois
    -0.06
     three
    -0.06
    Initially
    -0.06
     initial
    -0.06
     dulu
    -0.06
     сначала
    -0.06
    POSITIVE LOGITS
     Including
    0.07
    wale
    0.07
     !!
    0.06
     typeof
    0.06
     turnkey
    0.06
    軼
    0.06
     warga
    0.06
    န်း
    0.06
     worthwhile
    0.06
     پایان
    0.06
    Activations Density 0.031%

    No Known Activations