© 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. 120463
    Prev
    Next
    INDEX
    Explanations

    relies on

    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
    ឿង
    -0.07
     കൂടുതൽ
    -0.06
     swoją
    -0.06
     आमंत्रित
    -0.06
     أكثر
    -0.06
    ással
    -0.06
     começo
    -0.06
    主要
    -0.06
     सुरु
    -0.05
     reportedly
    -0.05
    POSITIVE LOGITS
     Neither
    0.08
     தாய்
    0.07
    Neither
    0.06
    পূর্বক
    0.06
     timely
    0.06
    特定の
    0.06
    prev
    0.06
     Fame
    0.06
     outskirts
    0.06
    낌
    0.06
    Activations Density 0.016%

    No Known Activations