© 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. 117531
    Prev
    Next
    INDEX
    Explanations

    supply zone, Part II, Biological Systems

    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
     langu
    -0.06
     rol
    -0.06
     συνεχ
    -0.06
     Midnight
    -0.06
     midnight
    -0.06
     continuous
    -0.06
     decis
    -0.06
     decidedly
    -0.06
     though
    -0.06
    աք
    -0.05
    POSITIVE LOGITS
     использует
    0.07
     insult
    0.06
     famosa
    0.06
     attentes
    0.06
     Москвы
    0.06
     사용
    0.06
     использование
    0.06
     obese
    0.06
     alleged
    0.06
     использовать
    0.06
    Activations Density 0.005%

    No Known Activations