© 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. 22-GEMMASCOPE-RES-131K
    7. 129140
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting the apostrophe‐s possessive marker (’s) on words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    possessive 's followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     faciliter
    -2.02
    peka
    -1.98
    thenburg
    -1.94
    FFECT
    -1.92
    涠
    -1.90
     bourg
    -1.89
     rapporter
    -1.88
    Brainz
    -1.88
    phans
    -1.87
     patienter
    -1.85
    POSITIVE LOGITS
    "
    2.55
    '
    2.20
     it
    1.91
     time
    1.85
     their
    1.70
     \
    1.69
    :
    1.67
     exquisite
    1.61
     or
    1.60
    ',
    1.59
    Activations Density 0.048%

    No Known Activations