© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120879
    Prev
    Next
    INDEX
    Explanations

    used done fixed recommendations

    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
    Negative Logits
     ಉತ್ಪನ್ನ
    -0.06
    いつでも
    -0.06
    };\
    -0.06
     स्पॉट
    -0.06
     उत्कृष्ट
    -0.06
     بعدی
    -0.06
     ويمكن
    -0.06
    🔥
    -0.06
    ](#
    -0.06
     formidable
    -0.06
    POSITIVE LOGITS
     този
    0.06
     випад
    0.06
     dissatisf
    0.06
     zadovol
    0.06
     takže
    0.06
     ব্যাক্ত
    0.06
     這個
    0.06
     नाते
    0.06
     príp
    0.05
     여기
    0.05
    Activations Density 0.046%

    No Known Activations