© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118742
    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
     बहुत
    -0.07
    飲食店
    -0.07
     भी
    -0.07
     هیچ
    -0.07
    彼の
    -0.06
     오히려
    -0.06
     म्हणून
    -0.06
     చాలా
    -0.06
     أيضا
    -0.06
     pantallas
    -0.06
    POSITIVE LOGITS
    ⏩
    0.06
     or
    0.06
    🐤
    0.05
     expertise
    0.05
    separator
    0.05
    ächst
    0.05
    anticipated
    0.05
    ou
    0.05
    or
    0.05
    📒
    0.05
    Activations Density 0.000%

    No Known Activations