© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13381
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

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

    The neuron is a detector for possessive pronouns (e.g. “my,” “your,” “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_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
     dando
    -1.22
     vía
    -1.22
     sám
    -1.20
     pourraient
    -1.17
     auront
    -1.16
     EVEN
    -1.15
     and
    -1.15
    ffion
    -1.13
    focused
    -1.13
     arbres
    -1.11
    POSITIVE LOGITS
     what
    1.80
     because
    1.52
     how
    1.46
    During
    1.45
     their
    1.45
    Often
    1.41
    When
    1.38
    Sometimes
    1.38
     oddly
    1.36
     unique
    1.34
    Activations Density 0.023%

    No Known Activations