© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130535
    Prev
    Next
    INDEX
    Explanations

    XML/HTML tags and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     provincial
    -0.06
     gemeinsam
    -0.06
    正常
    -0.06
     eligible
    -0.06
     dedicata
    -0.06
     বিনিয়োগ
    -0.06
     পরিচয়
    -0.06
     serían
    -0.06
     political
    -0.06
     segregation
    -0.06
    POSITIVE LOGITS
          
    0.06
    CK
    0.06
     HIV
    0.06
     also
    0.06
              
    0.06
     AIDS
    0.06
           
    0.06
     по
    0.06
     is
    0.06
     август
    0.06
    Activations Density 0.001%

    No Known Activations