© 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. 129082
    Prev
    Next
    INDEX
    Explanations

    operators and code syntax

    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
     to
    -0.07
    逐渐
    -0.06
    が
    -0.06
     دیگر
    -0.06
     neler
    -0.06
     gradually
    -0.06
    少了
    -0.06
    渐渐
    -0.06
     гораздо
    -0.06
     varied
    -0.06
    POSITIVE LOGITS
     evitar
    0.07
    avoid
    0.07
     éviter
    0.07
     avoid
    0.06
     обеспечить
    0.06
     menghindari
    0.06
     evitando
    0.06
     избе
    0.06
     أشهر
    0.06
     unless
    0.06
    Activations Density 0.003%

    No Known Activations