© 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. 118305
    Prev
    Next
    INDEX
    Explanations

    iterator, handle, range, first, while

    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
    हद
    -0.06
    目で
    -0.06
     הוד
    -0.06
    cü
    -0.06
     locating
    -0.06
    更大
    -0.05
     আকার
    -0.05
    ATHER
    -0.05
    larger
    -0.05
    到
    -0.05
    POSITIVE LOGITS
    嬿
    0.07
     two
    0.07
     tanggal
    0.07
     tremendously
    0.06
    এক
    0.06
     ধরনের
    0.06
     получи
    0.06
     bija
    0.06
     ihm
    0.06
     নহে
    0.06
    Activations Density 0.039%

    No Known Activations