© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120758
    Prev
    Next
    INDEX
    Explanations

    straight year

    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
     most
    -0.06
    most
    -0.06
     çoğu
    -0.06
    ばかり
    -0.06
     only
    -0.06
     除了
    -0.05
     compared
    -0.05
     usually
    -0.05
     Bereits
    -0.05
     meisten
    -0.05
    POSITIVE LOGITS
     различные
    0.07
     различных
    0.07
     ১০
    0.07
    Fundamental
    0.07
     συγκεκρι
    0.07
     diberikan
    0.07
     γίνεται
    0.07
     poderosa
    0.07
    Usage
    0.06
     mankind
    0.06
    Activations Density 0.066%

    No Known Activations