© 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. 121073
    Prev
    Next
    INDEX
    Explanations

    html/css selectors

    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
     பிரபலமான
    -0.07
     बीजेपी
    -0.06
    សា
    -0.06
     расположен
    -0.06
    अपनी
    -0.06
     gorgeous
    -0.06
     மத்தியில்
    -0.06
    hatikan
    -0.06
     Yani
    -0.06
    ună
    -0.06
    POSITIVE LOGITS
     under
    0.08
     lacking
    0.06
    Care
    0.06
    Virt
    0.06
     Find
    0.06
    ø
    0.06
     засто
    0.06
     цього
    0.05
     Sub
    0.05
     معظم
    0.05
    Activations Density 0.001%

    No Known Activations