© 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. 34-GEMMASCOPE-RES-131K
    7. 48298
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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_34/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
     Hers
    -1.23
     hers
    -1.15
    Hers
    -1.08
     mine
    -1.05
     Mine
    -1.00
    Mine
    -0.89
     mines
    -0.84
     my
    -0.80
     our
    -0.78
    kkelijk
    -0.77
    POSITIVE LOGITS
     theirs
    5.38
    irs
    3.75
     שלהם
    1.61
    yours
    1.60
     yours
    1.59
    IRS
    1.52
    Yours
    1.46
     THEIR
    1.44
     theres
    1.39
    their
    1.28
    Activations Density 0.027%

    No Known Activations