© 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. 120742
    Prev
    Next
    INDEX
    Explanations

    business and employment

    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
     db
    -0.06
     компо
    -0.06
     Company
    -0.06
     integration
    -0.06
    ாதீர்கள்
    -0.05
     compon
    -0.05
     пенсион
    -0.05
    Overall
    -0.05
     دب
    -0.05
     library
    -0.05
    POSITIVE LOGITS
     manzana
    0.07
     scegliere
    0.07
     choisi
    0.07
     escoger
    0.07
    危険
    0.06
    选择
    0.06
     elegir
    0.06
    選擇
    0.06
     choisir
    0.06
    ഞ്ച
    0.06
    Activations Density 0.036%

    No Known Activations