© 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. 129773
    Prev
    Next
    INDEX
    Explanations

    Professor Kolapo Olusola

    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
     экологи
    -0.07
     hybrid
    -0.06
    不再
    -0.06
     identiques
    -0.06
     använder
    -0.06
    deadline
    -0.06
     intégral
    -0.06
     instead
    -0.06
    agni
    -0.06
     использовать
    -0.06
    POSITIVE LOGITS
     श्रीवास्तव
    0.06
     perubahan
    0.06
     revisión
    0.06
     '*':
    0.05
     REQUIREMENTS
    0.05
    nCurrent
    0.05
     broadening
    0.05
    لمات
    0.05
     முதல
    0.05
    各种
    0.05
    Activations Density 0.001%

    No Known Activations