© 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. 49342
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by loss

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

    The neuron fires on personal possessive pronouns (my, her, its) when they occur in contexts of losing, regaining, or otherwise changing possession.

    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
    möglichen
    -0.93
     Moldova
    -0.90
    DECEMBER
    -0.89
     diskusi
    -0.88
     renforcer
    -0.88
     gauche
    -0.87
    arte
    -0.85
     SIMILAR
    -0.84
    Dian
    -0.83
     NECESS
    -0.82
    POSITIVE LOGITS
     composure
    1.41
     sanity
    1.26
     footing
    1.25
     bearings
    1.20
     dignity
    1.15
     cool
    1.09
     wits
    1.03
     appetite
    1.03
     integrity
    1.02
     humanity
    1.02
    Activations Density 0.018%

    No Known Activations