© 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. 120972
    Prev
    Next
    INDEX
    Explanations

    Read articles and introductions

    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
     tumbuh
    -0.07
     چھوڑ
    -0.06
     नोटबंदी
    -0.06
     २०१
    -0.06
     многих
    -0.06
    证明
    -0.06
     အမျိုး
    -0.06
    踱
    -0.06
     się
    -0.06
    就开始
    -0.06
    POSITIVE LOGITS
     any
    0.07
     যেকোন
    0.07
     হয়ত
    0.06
     the
    0.06
    ,.
    0.06
     एखाद्या
    0.05
     कुनै
    0.05
     덕
    0.05
     परिचाल
    0.05
    न्स
    0.05
    Activations Density 0.001%

    No Known Activations