© 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. 128115
    Prev
    Next
    INDEX
    Explanations

    include stdio.h

    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
     första
    -0.07
     ensimmä
    -0.06
    ก่อน
    -0.06
     первом
    -0.06
     первые
    -0.06
     Tavares
    -0.06
     dhad
    -0.06
     ersten
    -0.06
     первая
    -0.06
     πρώτη
    -0.06
    POSITIVE LOGITS
     mnoh
    0.06
     réfléch
    0.06
     শিক্ষা
    0.06
     map
    0.06
     Credit
    0.06
     wondering
    0.05
     azért
    0.05
     setempat
    0.05
     debating
    0.05
     《
    0.05
    Activations Density 0.001%

    No Known Activations