© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130391
    Prev
    Next
    INDEX
    Explanations

    alternatives or solutions

    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
     bunların
    -0.07
    여기
    -0.07
    ここで
    -0.06
    精心
    -0.06
     নষ্ট
    -0.06
    这是一个
    -0.06
     equine
    -0.06
    同样的
    -0.06
     pep
    -0.06
     atheist
    -0.06
    POSITIVE LOGITS
     المختلفة
    0.06
     solutions
    0.06
     можли
    0.06
     চেষ্ট
    0.06
    ře
    0.06
     gestalt
    0.06
     võimalik
    0.06
    oju
    0.06
     feasible
    0.06
     Chowdh
    0.05
    Activations Density 0.028%

    No Known Activations