© 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. 129153
    Prev
    Next
    INDEX
    Explanations

    HTML tags and select options

    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
    所以
    -0.06
     यानि
    -0.06
    因为
    -0.06
    िला
    -0.06
     Additional
    -0.06
    在这
    -0.06
     additional
    -0.06
    enjoy
    -0.06
    lieu
    -0.06
     ใน
    -0.06
    POSITIVE LOGITS
     variés
    0.07
    だけでなく
    0.07
    imsu
    0.06
     verschiedene
    0.06
    らを
    0.06
     alebo
    0.06
     számos
    0.06
     wiele
    0.06
     solves
    0.06
     différentes
    0.06
    Activations Density 0.003%

    No Known Activations