© 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. 119869
    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
                 
    -0.06
     செ
    -0.06
                    
    -0.06
              
    -0.06
     সমর্থকদের
    -0.06
                  
    -0.06
    而
    -0.06
                
    -0.06
     بجائے
    -0.06
    sneak
    -0.06
    POSITIVE LOGITS
     değişik
    0.07
     différente
    0.06
     каждом
    0.06
     různ
    0.06
    選択
    0.06
    народ
    0.06
    数十
    0.06
     CallbackContext
    0.06
     દરેક
    0.06
     różne
    0.06
    Activations Density 0.000%

    No Known Activations