© 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. 65599
    Prev
    Next
    INDEX
    Explanations

    possessives followed by specifics

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

    The neuron detects the possessive suffix "'s" attached to proper 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
     because
    -1.91
     indicates
    -1.84
     when
    -1.73
    Because
    -1.72
     some
    -1.70
     if
    -1.66
     using
    -1.66
     on
    -1.62
     what
    -1.60
     Because
    -1.55
    POSITIVE LOGITS
     renowned
    1.97
     superstar
    1.73
    fatalError
    1.72
    縞
    1.59
     cinq
    1.59
     famed
    1.57
     offre
    1.55
     doit
    1.54
    ฿
    1.52
    ⠀
    1.50
    Activations Density 0.040%

    No Known Activations