© 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. 79653
    Prev
    Next
    INDEX
    Explanations

    they, their, them

    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
     people
    -1.43
     students
    -1.28
     patients
    -1.24
     everyone
    -1.22
    ggings
    -1.21
    postolic
    -1.19
     users
    -1.16
     Deinen
    -1.14
     despues
    -1.14
    用户
    -1.12
    POSITIVE LOGITS
     their
    2.03
     they
    1.60
     themselves
    1.27
    他们
    1.27
     ihnen
    1.19
    their
    1.13
     mereka
    1.11
    他们的
    1.05
    Their
    1.00
     Mereka
    1.00
    Activations Density 0.122%

    No Known Activations