© 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. 129101
    Prev
    Next
    INDEX
    Explanations

    select or choose

    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
     درج
    -0.06
     এক্স
    -0.06
     একই
    -0.06
     می‌
    -0.06
     portable
    -0.06
     درجه
    -0.06
     gadget
    -0.06
    щие
    -0.05
     prejudices
    -0.05
     cached
    -0.05
    POSITIVE LOGITS
     kiezen
    0.08
    选择
    0.08
    の中から
    0.08
     choisir
    0.08
     выбрать
    0.07
     scelta
    0.07
     선택
    0.07
    的选择
    0.07
     takže
    0.07
    選択
    0.07
    Activations Density 0.049%

    No Known Activations