© 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. 118264
    Prev
    Next
    INDEX
    Explanations

    \

    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
     الجديدة
    -0.07
     with
    -0.06
     to
    -0.06
     জাক
    -0.06
    江苏
    -0.06
     skiers
    -0.06
     captivated
    -0.06
     সংগ্রামের
    -0.06
     వు
    -0.06
    atletas
    -0.06
    POSITIVE LOGITS
     what
    0.07
     później
    0.06
    还有
    0.06
    probably
    0.06
     évidemment
    0.06
    when
    0.06
    另一个
    0.06
    legends
    0.06
    whatever
    0.06
    Quel
    0.06
    Activations Density 0.004%

    No Known Activations