© 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. 119328
    Prev
    Next
    INDEX
    Explanations

    fuel and ethanol production

    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
     городской
    -0.08
    建築
    -0.07
    Einzel
    -0.07
     arquitect
    -0.07
    都市
    -0.07
    歳
    -0.06
    憋
    -0.06
     Einzel
    -0.06
     architect
    -0.06
    skyscraper
    -0.06
    POSITIVE LOGITS
    级别的
    0.06
     purpose
    0.06
     ethanol
    0.06
    linux
    0.06
     допъл
    0.06
     purposes
    0.06
     harms
    0.05
    替换
    0.05
     म्हट
    0.05
    是为了
    0.05
    Activations Density 0.004%

    No Known Activations