© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130770
    Prev
    Next
    INDEX
    Explanations

    exercise and fitness

    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
     for
    -0.06
     sufferings
    -0.06
     kült
    -0.06
     BBQ
    -0.06
    錯誤
    -0.06
    WHY
    -0.06
     SVM
    -0.05
     suffering
    -0.05
     vigor
    -0.05
     calme
    -0.05
    POSITIVE LOGITS
     Redirect
    0.08
     incredibly
    0.07
     Mounted
    0.06
     সামনের
    0.06
     cylindrical
    0.06
     Selling
    0.06
     theo
    0.06
     moeder
    0.06
     Interchange
    0.06
    click
    0.06
    Activations Density 0.009%

    No Known Activations