© 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. 119633
    Prev
    Next
    INDEX
    Explanations

    data structure definitions

    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
     comenz
    -0.07
    开始
    -0.07
     开始
    -0.07
     iniziare
    -0.07
     시작
    -0.07
     começar
    -0.07
    ansh
    -0.07
    rawberry
    -0.07
     প্রণ
    -0.06
    IRONMENT
    -0.06
    POSITIVE LOGITS
     hoof
    0.06
    basic
    0.06
    please
    0.06
     மட்டுமல்ல
    0.05
     payment
    0.05
    マーケット
    0.05
    market
    0.05
     দুর্ভাগ্য
    0.05
     뿐
    0.05
    bagai
    0.05
    Activations Density 0.001%

    No Known Activations