© 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. 116269
    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
     asshole
    -0.07
     सिर्फ
    -0.06
     actually
    -0.06
     resort
    -0.06
     केवळ
    -0.06
     it
    -0.06
     थिंक
    -0.06
     ত্রিশ
    -0.06
     แค
    -0.06
    checklist
    -0.06
    POSITIVE LOGITS
               
    0.06
     lifeline
    0.06
              
    0.06
                
    0.06
     zařízení
    0.06
     journeys
    0.06
    current
    0.06
    📲
    0.06
    hamed
    0.06
     shorter
    0.06
    Activations Density 0.000%

    No Known Activations