© 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. 129597
    Prev
    Next
    INDEX
    Explanations

    words following a parenthetical

    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
     eder
    -0.07
    теря
    -0.07
     supra
    -0.07
     全部
    -0.06
    игры
    -0.06
     الكتب
    -0.06
     against
    -0.06
    成人
    -0.06
     쓸
    -0.06
     perdido
    -0.06
    POSITIVE LOGITS
     ensures
    0.06
     विद्य
    0.06
    Этот
    0.06
     brasile
    0.06
     म्हणजेच
    0.06
     ensured
    0.06
     Brazilian
    0.06
     ভেতরে
    0.06
     sympathique
    0.05
     sauf
    0.05
    Activations Density 0.113%

    No Known Activations