© 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. 128478
    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
     those
    -0.08
    ),
    -0.07
     lowly
    -0.07
    ostructures
    -0.06
     boasting
    -0.06
     tiga
    -0.06
     way
    -0.06
    service
    -0.06
    co
    -0.06
     mysteriously
    -0.06
    POSITIVE LOGITS
    इस्
    0.06
     perubahan
    0.06
    ه‌ی
    0.06
    okane
    0.06
     সারাদেশে
    0.06
    দীর
    0.06
    𝗄
    0.06
    ariance
    0.05
    わりに
    0.05
    を受け
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.