© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120924
    Prev
    Next
    INDEX
    Explanations

    tree falling

    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
    Negative Logits
     misalnya
    -0.07
     bijvoorbeeld
    -0.07
     esimerkiksi
    -0.07
     مثلا
    -0.06
     예를
    -0.06
    pricht
    -0.06
    meye
    -0.06
    缮
    -0.06
     két
    -0.06
     například
    -0.06
    POSITIVE LOGITS
    我
    0.07
    我有
    0.06
    你
    0.06
     provide
    0.06
     그것
    0.06
    会有
    0.06
    蜘
    0.05
    類型
    0.05
    类型
    0.05
    जागरण
    0.05
    Activations Density 0.017%

    No Known Activations