© 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. 130542
    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
     including
    -0.06
    ↵↵
    -0.06
     krat
    -0.06
     one
    -0.06
     all
    -0.06
     Enemy
    -0.06
     एंड
    -0.05
     requesting
    -0.05
     用
    -0.05
     Donde
    -0.05
    POSITIVE LOGITS
     ተጨማሪ
    0.07
     recomenda
    0.07
     adicional
    0.06
     появ
    0.06
    விட
    0.06
    Pointer
    0.06
     tilbage
    0.06
     değil
    0.06
     paździer
    0.06
     пенсии
    0.06
    Activations Density 0.000%

    No Known Activations