© 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. 117509
    Prev
    Next
    INDEX
    Explanations

    $\pi$ radians or degrees

    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
    持續
    -0.07
     unei
    -0.06
     rambling
    -0.06
     cravings
    -0.06
    持续
    -0.06
     AUSTRAL
    -0.06
    ongono
    -0.06
     Otra
    -0.06
    meri
    -0.06
    AMA
    -0.06
    POSITIVE LOGITS
     유형
    0.06
     একেবারেই
    0.06
     atas
    0.06
     कदा
    0.06
     gif
    0.06
    types
    0.06
     where
    0.06
    意
    0.06
     പങ്കെടു
    0.06
     on
    0.06
    Activations Density 0.003%

    No Known Activations