© 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. 128447
    Prev
    Next
    INDEX
    Explanations

    functions with single letter arguments

    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
    将在
    -0.07
     स्पेशल
    -0.06
     जितने
    -0.06
     Temporal
    -0.06
     some
    -0.06
     all
    -0.06
    システムの
    -0.06
    系统中
    -0.06
     the
    -0.06
     времен
    -0.06
    POSITIVE LOGITS
    Understand
    0.07
    Algo
    0.07
    Bine
    0.06
     Understand
    0.06
     دیر
    0.06
    🛵
    0.06
    Though
    0.05
     тях
    0.05
     provided
    0.05
    umal
    0.05
    Activations Density 0.001%

    No Known Activations