© 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. 116466
    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
    Download
    -0.06
    ellan
    -0.06
    その
    -0.06
     последних
    -0.06
    😘
    -0.05
    eb
    -0.05
    .
    -0.05
     subscriptions
    -0.05
    ias
    -0.05
     धमाकेदार
    -0.05
    POSITIVE LOGITS
     directly
    0.07
     Direkt
    0.07
     pretože
    0.06
     enanti
    0.06
     ج
    0.06
    逐漸
    0.06
    接着
    0.06
     usare
    0.06
    Encript
    0.06
     ODBC
    0.06
    Activations Density 0.000%

    No Known Activations