© 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. 128306
    Prev
    Next
    INDEX
    Explanations

    energy-time entanglement and Heisenberg group

    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
     transmits
    -0.06
     droplets
    -0.06
     processes
    -0.06
     حدث
    -0.06
     নিয়ন্ত্রণে
    -0.06
    流程
    -0.06
     Maldives
    -0.06
     transmit
    -0.06
     شرح
    -0.06
     ሂደ
    -0.06
    POSITIVE LOGITS
    同時に
    0.07
    ✌
    0.07
     bounded
    0.06
     camouflage
    0.06
    겸
    0.06
    क्योंकि
    0.06
     제한
    0.06
     tumult
    0.06
     simultaneously
    0.06
     tới
    0.06
    Activations Density 0.001%

    No Known Activations