© 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. 128139
    Prev
    Next
    INDEX
    Explanations

    software and

    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
     swallowed
    -0.06
     نفسك
    -0.06
     altered
    -0.06
     نفسها
    -0.06
    While
    -0.06
     Surround
    -0.06
     notoriously
    -0.06
    はどう
    -0.06
     seriously
    -0.05
     messed
    -0.05
    POSITIVE LOGITS
     but
    0.07
     নিয়েছেন
    0.07
     নিয়েছে
    0.06
     웹
    0.06
     Republike
    0.06
     фраг
    0.06
     performs
    0.06
     Web
    0.06
     ঘোষনা
    0.06
     компен
    0.06
    Activations Density 0.002%

    No Known Activations