© 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. 118846
    Prev
    Next
    INDEX
    Explanations

    air conditioning or fuel treatment

    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
    observe
    -0.06
     dynam
    -0.06
     наблюда
    -0.06
    youtube
    -0.06
    拳
    -0.06
     transaction
    -0.06
     coval
    -0.05
     incent
    -0.05
     pouce
    -0.05
    лар
    -0.05
    POSITIVE LOGITS
     ऑल
    0.07
     წარმო
    0.06
     कर्मियों
    0.06
     बॅ
    0.06
    霏
    0.06
     Dopo
    0.06
     dopo
    0.06
     multipurpose
    0.06
     Após
    0.06
     दोस्तों
    0.06
    Activations Density 0.004%

    No Known Activations