© 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. 119889
    Prev
    Next
    INDEX
    Explanations

    boost mpl, fusion, developing, malawi, garden

    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
    不僅
    -0.08
    不仅
    -0.07
    不斷
    -0.07
    不但
    -0.07
    不断
    -0.06
     bleed
    -0.06
     Filtration
    -0.06
     billionaire
    -0.06
     ludicrous
    -0.06
     senden
    -0.06
    POSITIVE LOGITS
    राज्यपाल
    0.06
    这个问题
    0.06
     and
    0.06
    言葉
    0.05
     wszel
    0.05
     จึง
    0.05
     LGBTQ
    0.05
     to
    0.05
     Например
    0.05
    ↵
    0.05
    Activations Density 0.003%

    No Known Activations