© 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. 119499
    Prev
    Next
    INDEX
    Explanations

    language codes and strings

    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
     заяв
    -0.06
    الت
    -0.06
     керів
    -0.06
     Aside
    -0.06
     названия
    -0.06
     व्यापार
    -0.06
     सच्चाई
    -0.06
     ไฟ
    -0.05
     основ
    -0.05
     theoret
    -0.05
    POSITIVE LOGITS
    vgl
    0.06
    imilar
    0.06
     그러나
    0.06
     tidak
    0.06
     daha
    0.06
     mais
    0.06
    inio
    0.06
     semelhantes
    0.06
     Anschließend
    0.06
    aying
    0.06
    Activations Density 0.006%

    No Known Activations