© 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. 131023
    Prev
    Next
    INDEX
    Explanations

    internal details or utilities

    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
     الخارجية
    -0.07
    真
    -0.06
     externas
    -0.05
     QMessageBox
    -0.05
     before
    -0.05
    ʑ
    -0.05
    외
    -0.05
     providence
    -0.05
     inhibits
    -0.05
     真
    -0.05
    POSITIVE LOGITS
     dostęp
    0.06
     weighty
    0.06
    拡
    0.06
     intricate
    0.06
     numerous
    0.06
     či
    0.06
    Tyler
    0.06
     ample
    0.06
     lengthy
    0.06
     terus
    0.06
    Activations Density 0.001%

    No Known Activations