© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119335
    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
    Not in Any Lists

    No Comments

    Negative Logits
     সাহায্যের
    -0.06
    urias
    -0.06
     ohne
    -0.06
     without
    -0.06
     (!)
    -0.06
     ف
    -0.06
     case
    -0.06
     сове
    -0.06
     конференции
    -0.06
     без
    -0.05
    POSITIVE LOGITS
     officials
    0.07
     político
    0.07
     polít
    0.07
     полити
    0.07
    编写
    0.06
     għ
    0.06
     política
    0.06
     ২০১৬
    0.06
     bipartisan
    0.06
     political
    0.06
    Activations Density 0.000%

    No Known Activations