© 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. 120369
    Prev
    Next
    INDEX
    Explanations

    virus families

    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
    entan
    -0.06
     Patents
    -0.05
     spaw
    -0.05
     கட்டுமான
    -0.05
    出自
    -0.05
    生
    -0.05
     ampliamente
    -0.05
     இ
    -0.05
    oust
    -0.05
     speechSynthesis
    -0.05
    POSITIVE LOGITS
     appropriately
    0.06
     определение
    0.06
     définition
    0.06
     dingen
    0.06
     currently
    0.06
     създа
    0.06
     Faktor
    0.06
     beş
    0.06
     প্রভু
    0.06
    作成
    0.06
    Activations Density 0.009%

    No Known Activations