© 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. 119399
    Prev
    Next
    INDEX
    Explanations

    read and write operations

    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
    org
    -0.06
     trữ
    -0.06
    到
    -0.05
     आजाद
    -0.05
    ऊदी
    -0.05
    ewood
    -0.05
     জার্মান
    -0.05
    -
    -0.05
    Wild
    -0.05
    embry
    -0.05
    POSITIVE LOGITS
     CLIENT
    0.07
    =@@
    0.07
     клиент
    0.07
     업무
    0.07
     Более
    0.07
     klient
    0.07
     клиентов
    0.06
    𒆷
    0.06
     cliente
    0.06
    uyết
    0.06
    Activations Density 0.006%

    No Known Activations