© 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. 130872
    Prev
    Next
    INDEX
    Explanations

    calls and communication

    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
     मुख
    -0.06
    行走
    -0.06
     flex
    -0.06
    บริการ
    -0.05
     mesma
    -0.05
     symmetric
    -0.05
     modified
    -0.05
     new
    -0.05
    新的
    -0.05
     L
    -0.05
    POSITIVE LOGITS
     केवाईसी
    0.07
     secretary
    0.07
    Ε
    0.07
     frantically
    0.07
     treasurer
    0.07
     impatiently
    0.06
     interruptions
    0.06
     had
    0.06
     ছবি
    0.06
     категории
    0.06
    Activations Density 0.005%

    No Known Activations