© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103423
    Prev
    Next
    INDEX
    Explanations

    numbers or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ׇ
    -3.00
     botanique
    -2.09
     چربی
    -2.02
     گیاه
    -1.98
     الشاشة
    -1.96
    ֳ
    -1.88
     tumbuhan
    -1.84
     блюдо
    -1.81
     ویتامین
    -1.81
     प्रोड
    -1.81
    POSITIVE LOGITS
    ִּ
    2.53
    ַּ
    2.23
    ּוֹ
    2.22
     السياس
    2.09
    ↵
    1.95
    民众
    1.76
     they
    1.70
    וֹ
    1.68
     federal
    1.63
    を使
    1.59
    Activations Density 0.213%

    No Known Activations