© 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. 22-GEMMASCOPE-RES-131K
    7. 36334
    Prev
    Next
    INDEX
    Explanations

    pronouns it, them, its

    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_22/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
     to
    -1.60
     for
    -1.23
     and
    -1.12
    ,
    -1.04
      
    -0.87
    imetric
    -0.87
    tually
    -0.85
     sofern
    -0.85
    ONESIA
    -0.85
    ÊNCIAS
    -0.85
    POSITIVE LOGITS
     it
    4.13
     them
    3.14
     its
    2.89
    将其
    2.05
    它们
    1.89
    把它
    1.86
    它們
    1.78
    它
    1.77
     they
    1.67
    使其
    1.67
    Activations Density 0.100%

    No Known Activations