© 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. 117394
    Prev
    Next
    INDEX
    Explanations

    technical/specific systems

    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
     EACH
    -0.06
     प्रत्येक
    -0.06
     existing
    -0.06
     ফিল
    -0.06
     равен
    -0.06
     doctrine
    -0.06
     vorhand
    -0.05
     each
    -0.05
    izzare
    -0.05
     கப்ப
    -0.05
    POSITIVE LOGITS
    ственно
    0.07
     yummy
    0.06
     Jammu
    0.06
     самой
    0.06
     วัน
    0.06
    每日
    0.06
     sobre
    0.06
     社会
    0.06
    每天
    0.06
    Добрый
    0.06
    Activations Density 0.031%

    No Known Activations