© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119548
    Prev
    Next
    INDEX
    Explanations

    long durations, time, ages

    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
     внутри
    -0.07
    labyrinth
    -0.07
     publicized
    -0.06
     inside
    -0.06
     tussen
    -0.06
     tijdens
    -0.06
     👍
    -0.06
     giữa
    -0.06
     probed
    -0.06
     आधिकारिक
    -0.06
    POSITIVE LOGITS
    長期
    0.08
    长期
    0.07
     years
    0.07
     عمر
    0.07
     emeritus
    0.07
     long
    0.07
     सांस्कृतिक
    0.07
     Time
    0.07
     millennia
    0.06
     decades
    0.06
    Activations Density 0.001%

    No Known Activations