© 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. 130725
    Prev
    Next
    INDEX
    Explanations

    emotions and experiences

    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
     which
    -0.07
     जोड़ने
    -0.07
     by
    -0.06
     of
    -0.06
     والتي
    -0.06
     ostat
    -0.06
    どちら
    -0.06
    7
    -0.06
     whiche
    -0.06
    five
    -0.05
    POSITIVE LOGITS
    প্রশ্ন
    0.07
    তারপর
    0.07
    rayed
    0.07
     tinha
    0.07
     compounds
    0.07
     나의
    0.06
     onların
    0.06
     предложить
    0.06
    ิตย์
    0.06
     constricted
    0.06
    Activations Density 0.026%

    No Known Activations