© 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. 119327
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@CR]

    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
     while
    -0.06
    面前
    -0.06
     from
    -0.06
    <em>
    -0.06
     HM
    -0.06
     Scotland
    -0.06
     Keep
    -0.06
    omyel
    -0.06
     YOU
    -0.05
     after
    -0.05
    POSITIVE LOGITS
     исключительно
    0.07
     помимо
    0.07
     seren
    0.07
     suff
    0.06
     FileName
    0.06
     可愛い
    0.06
     ازيكم
    0.06
     ಅಲ್ಲಿ
    0.06
     uniquely
    0.06
     tilbage
    0.06
    Activations Density 0.009%

    No Known Activations