© 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. 128907
    Prev
    Next
    INDEX
    Explanations

    bloodstream infections

    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
     variáveis
    -0.07
     다양한
    -0.07
     versiones
    -0.07
     deverá
    -0.07
     Trainings
    -0.07
     değişken
    -0.07
     aplicación
    -0.06
     devotees
    -0.06
     çeşitli
    -0.06
    各式
    -0.06
    POSITIVE LOGITS
     building
    0.06
     relatively
    0.06
     بحيث
    0.06
     envisions
    0.05
     повы
    0.05
     обли
    0.05
     constructing
    0.05
     tax
    0.05
     повышения
    0.05
     leveled
    0.05
    Activations Density 0.006%

    No Known Activations