© 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. 128954
    Prev
    Next
    INDEX
    Explanations

    go to

    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
     europea
    -0.07
     निकाल
    -0.06
     aparecer
    -0.06
     Psychological
    -0.06
    normal
    -0.06
     JOptionPane
    -0.06
    пита
    -0.06
     hä
    -0.06
    کٹ
    -0.06
     normal
    -0.06
    POSITIVE LOGITS
     метод
    0.06
    \{-\
    0.06
     visant
    0.06
    依然
    0.06
    旨在
    0.05
    ৃদ্ধ
    0.05
     still
    0.05
     doğrudan
    0.05
     directo
    0.05
    still
    0.05
    Activations Density 0.018%

    No Known Activations