© 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. 34-GEMMASCOPE-RES-131K
    7. 90623
    Prev
    Next
    INDEX
    Explanations

    possessive her

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

    The neuron strongly activates on the feminine third‐person possessive pronoun “her.”

    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
     jego
    -1.77
    itmen
    -1.59
     его
    -1.56
    了他的
    -1.52
    ureusement
    -1.44
    Frei
    -1.41
    你们的
    -1.39
     kullanılan
    -1.39
    celotti
    -1.38
    Kemudian
    -1.32
    POSITIVE LOGITS
     own
    3.25
     herself
    3.20
    她
    2.25
     her
    2.13
    herself
    2.09
    self
    1.97
     she
    1.91
     husband
    1.88
     suaminya
    1.68
    her
    1.65
    Activations Density 0.032%

    No Known Activations