© 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. 130326
    Prev
    Next
    INDEX
    Explanations

    invention or optimization

    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
    还需要
    -0.07
     pelatihan
    -0.06
     giri
    -0.06
     učen
    -0.06
     Audiodate
    -0.06
     ಸೇರಿದ
    -0.06
     Script
    -0.06
    会在
    -0.06
    校长
    -0.06
     facilita
    -0.06
    POSITIVE LOGITS
     niches
    0.06
     सामु
    0.06
     еже
    0.06
     Judas
    0.05
    แบ่ง
    0.05
    ंत्रिक
    0.05
    Antes
    0.05
     herbaceous
    0.05
     কিন্তু
    0.05
    quela
    0.05
    Activations Density 0.003%

    No Known Activations