© 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. 129120
    Prev
    Next
    INDEX
    Explanations

    sell with

    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
    aman
    -0.06
     box
    -0.06
    ফিউ
    -0.06
     ke
    -0.06
     locations
    -0.06
     আঙ
    -0.06
     designations
    -0.06
    স্থলে
    -0.06
     exploring
    -0.05
     Karm
    -0.05
    POSITIVE LOGITS
     ativo
    0.07
     lentamente
    0.06
    춧
    0.06
     quay
    0.06
     excelente
    0.06
     ген
    0.06
     discounting
    0.06
    暂时
    0.06
    ড়ার
    0.06
     Guarantee
    0.06
    Activations Density 0.021%

    No Known Activations