© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118768
    Prev
    Next
    INDEX
    Explanations

    gmail addresses or email addresses

    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
     personalmente
    -0.07
     persönlich
    -0.07
     progressivement
    -0.06
    प्याज
    -0.06
     régulièrement
    -0.06
    公里
    -0.06
     in
    -0.06
    王的
    -0.06
    ంచరీలు
    -0.06
     बाघ
    -0.06
    POSITIVE LOGITS
    ansu
    0.06
    äume
    0.06
     better
    0.06
    寻求
    0.06
     exquisite
    0.05
    ``
    0.05
     सॉरी
    0.05
     Escape
    0.05
    の場合
    0.05
    findOrFail
    0.05
    Activations Density 0.012%

    No Known Activations