© 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. 129534
    Prev
    Next
    INDEX
    Explanations

    solutions to problems

    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
     intenta
    -0.07
     пыта
    -0.07
     attempt
    -0.06
     thinking
    -0.06
     سمجھ
    -0.06
    试图
    -0.06
     hoping
    -0.06
     try
    -0.06
     attempted
    -0.06
    ఇ
    -0.06
    POSITIVE LOGITS
     exciting
    0.07
     practica
    0.07
     if
    0.07
     dacă
    0.07
     charming
    0.06
    美丽的
    0.06
     اگر
    0.06
     fascinating
    0.06
    丰富的
    0.06
    तुरंग
    0.06
    Activations Density 0.014%

    No Known Activations