© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103953
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by a noun

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

    The neuron activates on the possessive suffix "'s" attached to names or nouns.

    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
    
    -1.59
    擽
    -1.56
     Hinblick
    -1.54
     bloquer
    -1.52
     adoro
    -1.52
    URRED
    -1.50
     wither
    -1.49
    
    -1.48
     terceros
    -1.48
    就是这样
    -1.47
    POSITIVE LOGITS
     by
    1.95
     to
    1.92
     as
    1.82
     in
    1.77
    "]));
    1.51
    }}{\
    1.49
     hvis
    1.45
     del
    1.45
     for
    1.43
     It
    1.41
    Activations Density 0.034%

    No Known Activations