© 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. 69054
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and family

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

    The neuron fires on mentions of the subject’s immediate family or close relatives (e.g. “with her family,” “with his wife,” “with my loving wife and kids”).

    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
     it
    -1.45
     into
    -1.30
     use
    -1.23
     which
    -1.23
     says
    -1.20
     they
    -1.15
     saying
    -1.13
     sent
    -1.13
     will
    -1.10
     there
    -1.10
    POSITIVE LOGITS
     соответству
    1.12
     함께
    1.07
     etre
    1.02
     fendi
    0.99
     conquête
    0.98
     fuir
    0.96
     Brésil
    0.95
     pouces
    0.94
     Tämä
    0.93
     Retrieves
    0.92
    Activations Density 0.012%

    No Known Activations