© 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. 129045
    Prev
    Next
    INDEX
    Explanations

    other languages

    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
     densely
    -0.07
     وعلى
    -0.06
    除非
    -0.06
     nearly
    -0.06
    すぐ
    -0.06
     first
    -0.06
    逐渐
    -0.06
     almost
    -0.06
     Nearly
    -0.06
    直到
    -0.06
    POSITIVE LOGITS
     অন্যান্য
    0.06
     अन्य
    0.06
    ;
    0.06
     diğer
    0.06
     direzione
    0.06
    その他の
    0.06
    ơ
    0.06
     other
    0.06
     andere
    0.06
    ቸው
    0.06
    Activations Density 0.013%

    No Known Activations