© 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. 117651
    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
     роки
    -0.06
     notorious
    -0.06
     eli
    -0.06
     preparation
    -0.06
    czki
    -0.06
    žil
    -0.06
    ﺐ
    -0.06
     aufgrund
    -0.06
    logic
    -0.06
    ড়ায়
    -0.06
    POSITIVE LOGITS
    enfants
    0.06
     सैलरी
    0.06
    感染
    0.06
     детей
    0.05
    Jersey
    0.05
     routinely
    0.05
     guideline
    0.05
     benutzt
    0.05
     sway
    0.05
     নৃত
    0.05
    Activations Density 0.000%

    No Known Activations