© 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. 128681
    Prev
    Next
    INDEX
    Explanations

    Nobel Peace Prize winners

    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
     असली
    -0.07
    రా
    -0.06
     one
    -0.06
     सर्वश्रेष्ठ
    -0.06
    واحد
    -0.06
    最
    -0.06
     eins
    -0.06
     Steinberg
    -0.06
     ম্যাচে
    -0.06
     ενός
    -0.06
    POSITIVE LOGITS
     now
    0.08
     теперь
    0.08
     nyní
    0.07
     ahora
    0.07
     bây
    0.06
     geschikt
    0.06
     જરૂર
    0.06
     اکنون
    0.06
    はよう
    0.06
     이제
    0.06
    Activations Density 0.006%

    No Known Activations