© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24939
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and abstract nouns

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

    The neuron consistently lights up on English personal pronouns (I, me, we, you, who, etc.) and related function words in sentences.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    impulan
    -1.02
     yup
    -1.00
     actually
    -1.00
    marché
    -0.97
     Actually
    -0.96
     Ultimately
    -0.94
     Yup
    -0.93
     Unternehmen
    -0.93
    잣
    -0.93
    之时
    -0.92
    POSITIVE LOGITS
    "]();
    1.01
     péché
    1.00
     culte
    0.98
    ips
    0.98
     onCancelled
    0.96
    による
    0.96
    seeded
    0.94
     ktorý
    0.93
    InstrumentedTest
    0.91
     vois
    0.90
    Activations Density 0.036%

    No Known Activations