© 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. 116955
    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
     با
    -0.07
     superbly
    -0.07
     với
    -0.06
     cleverly
    -0.06
     intending
    -0.06
     achieve
    -0.06
     excellently
    -0.06
     excellent
    -0.06
     have
    -0.06
     interesados
    -0.06
    POSITIVE LOGITS
     Mendez
    0.06
     burdensome
    0.06
    ຖ
    0.06
     चेन्नई
    0.06
     BAND
    0.05
    Accordingly
    0.05
    
    0.05
    このように
    0.05
     संपूर्ण
    0.05
     eraser
    0.05
    Activations Density 0.000%

    No Known Activations