© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130183
    Prev
    Next
    INDEX
    Explanations

    array and list usage

    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
     வகை
    -0.07
     স্থির
    -0.06
     ശക്തി
    -0.06
     popularity
    -0.06
    irat
    -0.06
     चीज
    -0.06
    dann
    -0.06
     কিছু
    -0.05
     chemists
    -0.05
     शामिल
    -0.05
    POSITIVE LOGITS
     گراف
    0.06
     புதிய
    0.06
    สุดท้าย
    0.06
     পাঠানোর
    0.06
     থে
    0.06
     colaborar
    0.06
    opie
    0.06
     твор
    0.06
    ສົ່ງ
    0.06
     stör
    0.06
    Activations Density 0.010%

    No Known Activations