© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 80054
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and courts

    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_22/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
     '';
    -1.32
     dani
    -1.29
     lidl
    -1.28
     الجلد
    -1.27
     ivel
    -1.27
     Cantidad
    -1.23
     vanil
    -1.22
     asos
    -1.22
     yves
    -1.20
     razonable
    -1.20
    POSITIVE LOGITS
     so
    1.65
     procedure
    1.62
    Ἐ
    1.43
    ּוֹ
    1.41
     设置
    1.38
     procedural
    1.38
    ִּ
    1.37
     procedures
    1.36
    ικοί
    1.35
     proceedings
    1.34
    Activations Density 0.100%

    No Known Activations