© 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. 116539
    Prev
    Next
    INDEX
    Explanations

    UI elements and programming

    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
     after
    -0.08
    hile
    -0.07
     Bookmark
    -0.06
     بعد
    -0.06
     vorm
    -0.06
     bookmark
    -0.06
     после
    -0.06
     while
    -0.06
     dopo
    -0.06
     glued
    -0.06
    POSITIVE LOGITS
    专用
    0.07
     jeweiligen
    0.06
    specific
    0.06
     jeweil
    0.06
    创新
    0.06
    পাত্র
    0.06
     Renaissance
    0.06
    其他
    0.06
    podcast
    0.06
    特定的
    0.06
    Activations Density 0.001%

    No Known Activations