© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33281
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to groups

    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
     was
    -1.69
     it
    -1.53
     its
    -1.49
     your
    -1.49
     itself
    -1.22
     you
    -1.20
    它是
    -1.17
    它
    -1.15
    它的
    -1.12
     just
    -1.09
    POSITIVE LOGITS
     they
    4.78
     their
    4.13
    他们
    3.20
     themselves
    3.02
    Their
    2.95
     jejich
    2.91
    他們
    2.91
    They
    2.81
     mereka
    2.78
     их
    2.77
    Activations Density 0.071%

    No Known Activations