© 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. 117059
    Prev
    Next
    INDEX
    Explanations

    first, first, first

    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
    ੌ
    -0.06
    提到的
    -0.06
     of
    -0.06
    ुर
    -0.05
    ureux
    -0.05
     везде
    -0.05
    бов
    -0.05
    ļu
    -0.05
    ៊
    -0.05
    gangen
    -0.05
    POSITIVE LOGITS
     첫
    0.07
    첫
    0.07
    )
    0.06
    】
    0.06
     dislike
    0.06
     grou
    0.06
     перший
    0.06
    ไม่ได้
    0.06
     &
    0.06
     پہلی
    0.06
    Activations Density 0.005%

    No Known Activations