© 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. 10-GEMMASCOPE-RES-131K
    7. 73201
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by actions

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

    The neuron is responding to personal pronouns and other words that mark direct reference to people (e.g. I/you/him/her/them).

    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
     it
    -2.56
     that
    -2.23
     would
    -2.08
     if
    -2.08
     can
    -1.94
     medalla
    -1.86
    {
    -1.80
     could
    -1.73
     дорогой
    -1.72
    名叫
    -1.70
    POSITIVE LOGITS
    section
    1.87
     staten
    1.80
     FINALLY
    1.80
     jurassic
    1.76
     コート
    1.74
     lefs
    1.67
     lakers
    1.66
     broder
    1.63
     moter
    1.63
     barnet
    1.63
    Activations Density 0.020%

    No Known Activations