© 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. 117221
    Prev
    Next
    INDEX
    Explanations

    ofsuchdemothislikely(एनसीआरटीএরূপ

    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
     нет
    -0.06
     नाही
    -0.06
    iseksi
    -0.06
     silently
    -0.06
     എല്ലാം
    -0.06
     Sicht
    -0.06
     være
    -0.06
     كان
    -0.06
    塑料
    -0.06
     চোখ
    -0.06
    POSITIVE LOGITS
     of
    0.06
     such
    0.06
     demo
    0.06
     this
    0.06
                
    0.06
    likely
    0.06
    (
    0.06
     एनसीआरटी
    0.06
                 
    0.06
     এরূপ
    0.06
    Activations Density 0.012%

    No Known Activations