Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8493
    Prev
    Next
    INDEX
    Explanations

    feminine singular 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
     himself
    -2.25
     his
    -1.87
     esso
    -1.67
     jego
    -1.54
     he
    -1.51
     celui
    -1.49
     usarlo
    -1.47
     его
    -1.44
     který
    -1.38
    himself
    -1.38
    POSITIVE LOGITS
     herself
    3.69
     she
    3.44
     celle
    2.89
     она
    2.83
     которой
    2.80
     her
    2.78
     которая
    2.67
     laquelle
    2.63
     quella
    2.55
    herself
    2.52
    Activations Density 0.041%

    No Known Activations