© 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. 39648
    Prev
    Next
    INDEX
    Explanations

    our and my followed by nouns

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

    The neuron strongly activates on possessive pronouns (especially “our,” but also “my” and “your”), flagging expressions of ownership or association.

    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
    considered
    -1.68
    primarily
    -1.62
    commonly
    -1.58
     apparaissent
    -1.58
     immense
    -1.57
     dando
    -1.56
     the
    -1.56
     heeft
    -1.50
    presented
    -1.50
     unn
    -1.47
    POSITIVE LOGITS
    晅
    1.71
     by
    1.71
      
    1.67
     people
    1.66
     with
    1.66
     first
    1.57
    ”、“
    1.57
     burgeoning
    1.55
    $,
    1.53
     journalist
    1.53
    Activations Density 0.094%

    No Known Activations