© 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. 119778
    Prev
    Next
    INDEX
    Explanations

    types classification kinds

    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
    选择
    -0.07
    選擇
    -0.07
     там
    -0.07
     einfache
    -0.07
     다른
    -0.06
     व
    -0.06
     eenvoud
    -0.06
     ¿?
    -0.06
     вариант
    -0.06
    簡易
    -0.06
    POSITIVE LOGITS
     such
    0.07
     مثل
    0.07
    类型
    0.07
     has
    0.07
     typ
    0.07
     is
    0.06
    types
    0.06
     humankind
    0.06
     አይነት
    0.06
     isinstance
    0.06
    Activations Density 0.002%

    No Known Activations