© 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. 130584
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parentheses or numbers

    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
     без
    -0.07
     heeft
    -0.07
     WHILE
    -0.06
    の部分
    -0.06
     đều
    -0.06
     بدون
    -0.06
     khi
    -0.06
     nếu
    -0.06
     будут
    -0.06
     is
    -0.06
    POSITIVE LOGITS
    However
    0.08
    laptop
    0.06
     However
    0.06
     toutefois
    0.06
     Toutefois
    0.06
     presente
    0.06
     experimented
    0.06
    crystall
    0.06
     reass
    0.05
     Carp
    0.05
    Activations Density 0.001%

    No Known Activations