© 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. 10-GEMMASCOPE-RES-131K
    7. 104307
    Prev
    Next
    INDEX
    Explanations

    possessive before personal noun

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

    The neuron is selectively activating on third‐person possessive pronouns (e.g. “his,” “her,” “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_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
    0
    -1.76
     if
    -1.70
     people
    -1.70
     is
    -1.58
     Repubblica
    -1.55
     things
    -1.49
     the
    -1.47
     should
    -1.46
    ではまた
    -1.46
     value
    -1.45
    POSITIVE LOGITS
    wendigkeit
    1.45
    峁
    1.44
    wasn
    1.41
    也不
    1.35
     –
    1.34
    mű
    1.32
    馁
    1.30
     qualsiasi
    1.30
    丶
    1.30
     kurzem
    1.30
    Activations Density 0.030%

    No Known Activations