© 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. 120667
    Prev
    Next
    INDEX
    Explanations

    gold, oil, precious metals

    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
     info
    -0.06
     demo
    -0.06
     inform
    -0.05
     informer
    -0.05
     এর
    -0.05
    шої
    -0.05
    蓊
    -0.05
     phenomena
    -0.05
    ッズ
    -0.05
     demos
    -0.05
    POSITIVE LOGITS
    規模
    0.07
     मकसद
    0.06
     цель
    0.06
     compless
    0.06
     nedeniyle
    0.06
    目标
    0.06
     प्रत्येक
    0.06
    ☦
    0.06
     handlebars
    0.06
    规模
    0.06
    Activations Density 0.002%

    No Known Activations