© 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. 118366
    Prev
    Next
    INDEX
    Explanations

    for any

    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
     především
    -0.07
    主に
    -0.07
     spezi
    -0.07
     преимущественно
    -0.07
     주로
    -0.07
     mainly
    -0.07
     様
    -0.07
     głównie
    -0.07
     terutama
    -0.06
     primarily
    -0.06
    POSITIVE LOGITS
    encryption
    0.06
    始める
    0.06
    ->"
    0.06
     følgende
    0.06
     weiteres
    0.06
    religious
    0.06
    allar
    0.06
     Contributors
    0.05
     আরম্ভ
    0.05
    indu
    0.05
    Activations Density 0.001%

    No Known Activations