© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59583
    Prev
    Next
    INDEX
    Explanations

    possessive phrases

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

    The neuron is detecting the possessive pronoun “their.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    quatch
    -1.63
     jego
    -1.60
    thenburg
    -1.47
     его
    -1.45
    ulite
    -1.45
    ynthesis
    -1.44
     carnage
    -1.42
     uphe
    -1.38
     entrepre
    -1.34
    мога
    -1.34
    POSITIVE LOGITS
     own
    4.16
     their
    3.08
    Their
    2.98
     respective
    2.72
     Their
    2.66
     themselves
    2.63
    their
    2.41
    他们的
    2.08
    selves
    2.00
     THEIR
    1.98
    Activations Density 0.092%

    No Known Activations