© 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. 129509
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
     ধরেই
    -0.06
     पारंपरिक
    -0.06
    ूँ
    -0.06
     because
    -0.06
     its
    -0.06
    因为它
    -0.06
    儀
    -0.05
     customarily
    -0.05
     کمان
    -0.05
    原生
    -0.05
    POSITIVE LOGITS
     قلب
    0.07
     每个
    0.07
    Deserialize
    0.06
     Bedarf
    0.06
     wildflower
    0.06
    䅛
    0.06
     nötig
    0.06
    পের
    0.06
    ถนน
    0.06
     операций
    0.06
    Activations Density 0.002%

    No Known Activations