© 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. 47996
    Prev
    Next
    INDEX
    Explanations

    my or your followed by a relation or favorite thing

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

    The neuron activates on first- and second-person possessive pronouns (e.g. “my” and “your”).

    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
     of
    -2.16
     тыся
    -1.94
     laterales
    -1.83
    bundet
    -1.70
     ieder
    -1.70
    叆
    -1.69
     obyvateľov
    -1.66
    怎麼
    -1.66
     gekocht
    -1.66
    总是
    -1.65
    POSITIVE LOGITS
    </h1>
    2.39
     a
    2.02
    1.98
    (
    1.96
     vacía
    1.95
     only
    1.93
     more
    1.66
     Such
    1.64
     Despite
    1.63
    </h2>
    1.60
    Activations Density 0.026%
    No Known Activations