© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130794
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and processes

    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
     αλλά
    -0.07
    但
    -0.07
     nhưng
    -0.07
     하지만
    -0.07
    稱為
    -0.07
     тоді
    -0.07
    由于
    -0.06
     heartfelt
    -0.06
     τότε
    -0.06
    但也
    -0.06
    POSITIVE LOGITS
     from
    0.08
     in
    0.07
     by
    0.07
    Kiev
    0.06
     program
    0.06
    怼
    0.06
    อกาส
    0.05
     프로그램
    0.05
     on
    0.05
    争
    0.05
    Activations Density 0.048%

    No Known Activations