© 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. 120518
    Prev
    Next
    INDEX
    Explanations

    links and urls

    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
     funcionan
    -0.07
     testa
    -0.07
     largos
    -0.07
     acontece
    -0.07
    割合
    -0.06
     ভূমিকা
    -0.06
    োপাধ্যা
    -0.06
    模式
    -0.06
     Análisis
    -0.06
     enn
    -0.06
    POSITIVE LOGITS
     first
    0.06
     нерав
    0.05
    yb
    0.05
     впервые
    0.05
     সর্বপ্রথম
    0.05
    chus
    0.05
     novices
    0.05
     Luz
    0.05
    first
    0.05
    icos
    0.05
    Activations Density 0.001%

    No Known Activations