© 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. 10-GEMMASCOPE-RES-131K
    7. 20077
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on personal pronouns (e.g. I, you, they, it, there) rather than content words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     medarbe
    -1.50
     ACTUAL
    -1.48
     aussit
    -1.48
    通过
    -1.48
     SimpleName
    -1.45
     visse
    -1.44
     Ilmu
    -1.43
    Ѥ
    -1.43
    ется
    -1.37
    ⅼ
    -1.37
    POSITIVE LOGITS
     it
    1.75
     as
    1.70
     because
    1.68
     there
    1.64
     for
    1.42
     The
    1.39
    不然
    1.36
     part
    1.34
     wasn
    1.34
     just
    1.31
    Activations Density 0.087%

    No Known Activations