© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130692
    Prev
    Next
    INDEX
    Explanations

    coordinate scaling vector field

    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
    常量
    -0.06
     Krit
    -0.06
    只有一个
    -0.06
     ഒന്ന്
    -0.06
     enige
    -0.06
     sizes
    -0.06
     destructor
    -0.06
     وأن
    -0.05
     jedna
    -0.05
     সারাদেশে
    -0.05
    POSITIVE LOGITS
     visitor
    0.06
     প্রধানমন্ত্রীর
    0.06
     visit
    0.06
    visit
    0.06
    routing
    0.06
     നേരി
    0.06
     perspective
    0.06
    navigationItem
    0.06
    visitor
    0.06
     atmosfera
    0.06
    Activations Density 0.003%

    No Known Activations