© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131042
    Prev
    Next
    INDEX
    Explanations

    case presentation

    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
     when
    -0.08
    嘗試
    -0.07
     inicial
    -0.07
     Cuando
    -0.07
     새로운
    -0.07
     новой
    -0.07
     neuen
    -0.07
     When
    -0.07
     когда
    -0.07
     kiedy
    -0.07
    POSITIVE LOGITS
    ↵
    0.05
     laboral
    0.05
    目前
    0.05
     upkeep
    0.05
    相关
    0.05
    Lazy
    0.05
    ładow
    0.05
    спорт
    0.05
    替
    0.05
    лаш
    0.05
    Activations Density 0.001%

    No Known Activations