© 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. 117421
    Prev
    Next
    INDEX
    Explanations

    optical and electronic devices

    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
     overeen
    -0.06
    ポ
    -0.06
    宣言
    -0.05
     বিভিন্ন
    -0.05
    alur
    -0.05
     thanks
    -0.05
    urut
    -0.05
    ＇
    -0.05
     ока
    -0.05
     eternity
    -0.05
    POSITIVE LOGITS
    involved
    0.07
     permettre
    0.07
     permettant
    0.07
     folosit
    0.06
    ंपेक्षा
    0.06
     Involved
    0.06
     для
    0.06
     vervangen
    0.06
     το
    0.06
    ជាប់
    0.06
    Activations Density 0.053%

    No Known Activations