© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130219
    Prev
    Next
    INDEX
    Explanations

    numbers or enumerations

    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
    ではありません
    -0.07
    没有什么
    -0.07
     bisnis
    -0.06
     nicht
    -0.06
    Delete
    -0.06
    を除く
    -0.06
     тради
    -0.06
    जनों
    -0.06
    nicht
    -0.06
     not
    -0.06
    POSITIVE LOGITS
     that
    0.07
     дум
    0.06
    jed
    0.05
     unfilled
    0.05
     drilled
    0.05
    respons
    0.05
     Ether
    0.05
     dreamt
    0.05
    ').
    0.05
     hole
    0.05
    Activations Density 0.002%

    No Known Activations