© 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. 117251
    Prev
    Next
    INDEX
    Explanations

    **time passing like long periods**

    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
     zwei
    -0.07
     något
    -0.07
     관련된
    -0.07
     sommige
    -0.07
     sogenannte
    -0.07
     bijna
    -0.07
     até
    -0.06
     meisten
    -0.06
     दोन
    -0.06
     sogenannten
    -0.06
    POSITIVE LOGITS
     употре
    0.06
    ρύ
    0.06
     தீங்கு
    0.06
    運用
    0.06
     enfat
    0.05
    Insufficient
    0.05
    enum
    0.05
     रेजि
    0.05
    SPACE
    0.05
    asion
    0.05
    Activations Density 0.019%

    No Known Activations