© 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. 68317
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by action

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

    This neuron activates on personal referring expressions—especially sentence-subject pronouns (I, he, she) and character names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     phénom
    -1.49
     DÍA
    -1.45
     termé
    -1.44
     régal
    -1.44
    comida
    -1.41
     obrázok
    -1.41
     sobot
    -1.40
    telep
    -1.38
     SEÑ
    -1.38
    értel
    -1.36
    POSITIVE LOGITS
     again
    1.65
     further
    1.39
     open
    1.38
     back
    1.36
     opened
    1.30
     turned
    1.29
     continue
    1.24
     said
    1.22
     closer
    1.20
     finally
    1.20
    Activations Density 0.004%

    No Known Activations