© 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. 131057
    Prev
    Next
    INDEX
    Explanations

    gained the seat

    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
     Kampf
    -0.07
    ছু
    -0.06
     आघाडी
    -0.06
     Examine
    -0.06
    examine
    -0.06
    侕
    -0.06
    ár
    -0.06
     declaró
    -0.06
     스스로
    -0.06
     choirs
    -0.06
    POSITIVE LOGITS
    .
    0.07
    साईट
    0.06
    越来越
    0.05
     learnt
    0.05
    iet
    0.05
     dram
    0.05
    جنة
    0.05
     Having
    0.05
     having
    0.05
    越來越
    0.05
    Activations Density 0.002%

    No Known Activations