© 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. 117175
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    原理
    -0.07
    撹
    -0.07
     érz
    -0.07
     Gdy
    -0.06
    లే
    -0.06
    报错
    -0.06
    开展
    -0.06
     partition
    -0.06
     TiO
    -0.06
    ucers
    -0.06
    POSITIVE LOGITS
     толькі
    0.07
     सिर्फ
    0.07
     wielu
    0.06
     apenas
    0.06
     только
    0.06
     zahlreiche
    0.06
     również
    0.06
    arrow
    0.06
     রাজধানী
    0.06
     pouze
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.