© 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. 120977
    Prev
    Next
    INDEX
    Explanations

    various contexts and formats

    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
    כן
    -0.06
    )
    -0.06
    案内
    -0.06
    )|
    -0.06
     travaille
    -0.06
     العاشر
    -0.06
     Département
    -0.06
    anhyd
    -0.06
    情況
    -0.05
     фактически
    -0.05
    POSITIVE LOGITS
     ক্যাম্প
    0.06
    ह
    0.06
     δεν
    0.05
     လက်
    0.05
     counterpart
    0.05
     חלק
    0.05
    lebot
    0.05
    ছাই
    0.05
    modified
    0.05
     দশমিক
    0.05
    Activations Density 0.001%

    No Known Activations