© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72301
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

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

    The neuron fires strongly on possessive markers—tokens like “my,” “his,” “their,” “your,” or the ’s suffix—i.e. words indicating possession.

    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
     I
    -1.80
    *}{
    -1.59
    さんも
    -1.55
    ="
    -1.54
    *
    -1.52
    ⬈
    -1.50
    "
    -1.48
    +
    -1.47
    :
    -1.46
    已经在
    -1.45
    POSITIVE LOGITS
     how
    2.91
     what
    1.98
     which
    1.98
     this
    1.95
    kön
    1.89
     öde
    1.73
     排骨
    1.72
    瑒
    1.63
    豨
    1.63
     their
    1.60
    Activations Density 0.069%

    No Known Activations