© 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. 118217
    Prev
    Next
    INDEX
    Explanations

    "-o `"

    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
     mentoring
    -0.06
     சென்று
    -0.06
    不但
    -0.06
     phenomena
    -0.06
     نتيجة
    -0.06
     invests
    -0.06
     одновременно
    -0.06
     ইংরেজি
    -0.06
     decentralized
    -0.06
    жом
    -0.06
    POSITIVE LOGITS
     that
    0.07
     currently
    0.06
     κάπο
    0.06
    抬头
    0.06
    裤
    0.06
     stalling
    0.06
    anca
    0.05
     namely
    0.05
    मेटिक
    0.05
     blanco
    0.05
    Activations Density 0.001%

    No Known Activations