© 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. 10-GEMMASCOPE-RES-131K
    7. 47707
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
    ۱۹
    -1.36
     także
    -1.32
    الأ
    -1.30
    الر
    -1.29
    vocato
    -1.27
    visel
    -1.27
    年
    -1.27
     泥
    -1.27
    Autres
    -1.26
    JON
    -1.26
    POSITIVE LOGITS
     they
    2.80
     their
    1.99
     Their
    1.80
    1
    1.55
     lakini
    1.51
     then
    1.46
     They
    1.41
     seems
    1.37
    their
    1.34
     even
    1.32
    Activations Density 0.028%

    No Known Activations