© 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. 119537
    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
     മാറി
    -0.07
     your
    -0.07
     if
    -0.06
     പിന്നീട്
    -0.06
     Paragraph
    -0.06
     অর্থাৎ
    -0.06
    修改
    -0.06
     redire
    -0.05
     oliv
    -0.05
     vergessen
    -0.05
    POSITIVE LOGITS
     meskipun
    0.06
     strikingly
    0.06
     crucial
    0.06
     portent
    0.06
     Moody
    0.06
     риск
    0.06
     ။
    0.06
     категори
    0.06
     dalam
    0.06
     decidedly
    0.06
    Activations Density 0.000%

    No Known Activations