© 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. 71551
    Prev
    Next
    INDEX
    Explanations

    possessive nouns characteristics

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

    The main thing this neuron does is detect the genitive or contraction suffix "'s" attached to words.

    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
     ficou
    -1.67
     Bedürf
    -1.65
     pequeno
    -1.65
     testemun
    -1.64
    良かったです
    -1.64
    Nuevas
    -1.63
    Consigli
    -1.62
     nuevos
    -1.61
    ならでは
    -1.61
    
    -1.60
    POSITIVE LOGITS
     before
    1.91
    t
    1.91
     when
    1.84
    c
    1.82
     this
    1.63
    m
    1.63
     because
    1.57
    wwwww
    1.54
     during
    1.52
     despite
    1.52
    Activations Density 0.075%

    No Known Activations