© 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. 117304
    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
     rainbows
    -0.06
    物联网
    -0.06
    ЗА
    -0.06
     Gazz
    -0.06
     २०१
    -0.06
    isées
    -0.06
    lable
    -0.06
    based
    -0.06
    كام
    -0.05
     handic
    -0.05
    POSITIVE LOGITS
     niewiel
    0.07
    组织
    0.07
     organisasi
    0.07
    組織
    0.06
     mempertahankan
    0.06
     请求
    0.06
     örg
    0.06
     নগর
    0.06
     experienced
    0.06
    层
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.