© 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. 116013
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     فونب
    -0.08
    माइंडर
    -0.07
     BusABC
    -0.07
     बिकॉज
    -0.07
    اونلوډ
    -0.07
    যানী
    -0.07
     কথোপ
    -0.07
     ও
    -0.07
     কচের
    -0.07
     ইনডাক
    -0.07
    POSITIVE LOGITS
     Deity
    0.06
     Crete
    0.06
    神的
    0.05
    曜
    0.05
     ausreiche
    0.05
    Ionic
    0.05
     proyek
    0.05
    足够
    0.05
     थीं
    0.05
     admitted
    0.05
    Activations Density 0.000%

    No Known Activations