© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32599
    Prev
    Next
    INDEX
    Explanations

    possessive his or himself

    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
    Their
    -2.30
     mereka
    -2.23
    They
    -2.23
     they
    -2.20
     leur
    -2.11
     leurs
    -2.03
    they
    -1.97
     вона
    -1.96
     которое
    -1.94
     They
    -1.84
    POSITIVE LOGITS
     his
    11.44
     himself
    5.53
     его
    4.97
     jego
    4.91
    他的
    4.22
     seinem
    4.22
     seiner
    4.03
    his
    3.91
     njego
    3.84
     hänen
    3.72
    Activations Density 0.554%

    No Known Activations