© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90654
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns following prepositions

    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
     only
    -2.38
    Some
    -1.90
    ൎ
    -1.88
     bym
    -1.63
     some
    -1.58
    Only
    -1.56
     этом
    -1.48
     approu
    -1.48
     аппети
    -1.48
     Weltkrieg
    -1.47
    POSITIVE LOGITS
     its
    3.08
     his
    2.28
     swojego
    1.85
     swoich
    1.84
     your
    1.80
     svoje
    1.77
    ± 
    1.68
     swojej
    1.64
     основных
    1.61
     ње
    1.61
    Activations Density 0.162%

    No Known Activations