© 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. 120367
    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
     Namely
    -0.06
     Gu
    -0.06
     Highly
    -0.06
     hervor
    -0.05
     सम्पूर्ण
    -0.05
     ट्यूब
    -0.05
    ില
    -0.05
     totality
    -0.05
    ಗು
    -0.05
     yemek
    -0.05
    POSITIVE LOGITS
     அமைக்க
    0.07
    simpleType
    0.06
    SYSTEM
    0.06
     différentes
    0.06
     thấp
    0.06
     প্রাপ
    0.06
    著名
    0.06
    American
    0.06
     Dạ
    0.06
     établissements
    0.06
    Activations Density 0.000%

    No Known Activations