© 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. 127193
    Prev
    Next
    INDEX
    Explanations

    personal pronouns like I and you

    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
     have
    -1.41
    我们
    -1.36
    cibles
    -1.24
     kriminal
    -1.23
    如
    -1.21
    鯔
    -1.20
    tså
    -1.20
     Novembre
    -1.20
     arkiv
    -1.20
     konkre
    -1.18
    POSITIVE LOGITS
    するに
    1.24
     особенно
    1.24
     kleines
    1.23
     eventual
    1.22
    nts
    1.22
     n
    1.20
    .
    1.16
     Denken
    1.15
     engagé
    1.14
     You
    1.13
    Activations Density 0.021%

    No Known Activations