© 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. 128594
    Prev
    Next
    INDEX
    Explanations

    mathematical variable and symbol notation

    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
     while
    -0.07
     when
    -0.07
     போக்குவர
    -0.07
     عندما
    -0.06
     simulate
    -0.06
     enquanto
    -0.06
     mientras
    -0.06
     когда
    -0.06
    वेळी
    -0.06
     potentially
    -0.06
    POSITIVE LOGITS
     more
    0.07
    ;
    0.07
    :
    0.07
    Ĉ
    0.07
    发送
    0.07
     말고
    0.06
    ட்டிக்
    0.06
     slick
    0.06
     zašt
    0.06
     leaderboard
    0.06
    Activations Density 0.006%

    No Known Activations