© 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. 130124
    Prev
    Next
    INDEX
    Explanations

    controls and display settings

    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
     it
    -0.07
     animals
    -0.07
     enviable
    -0.06
     animali
    -0.06
     אם
    -0.06
    basketball
    -0.06
     adequate
    -0.06
     Adequate
    -0.06
     Warning
    -0.06
     biblioteca
    -0.06
    POSITIVE LOGITS
    showing
    0.06
     Pharm
    0.06
    Pharm
    0.06
    comparing
    0.05
    effer
    0.05
    側面
    0.05
     लिंक
    0.05
     نفسي
    0.05
     comparison
    0.05
    人気の
    0.05
    Activations Density 0.003%

    No Known Activations