© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84366
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people's actions or possessions

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

    The neuron is highly sensitive to third-person pronouns (e.g. he, him, his, it) referring back to previously mentioned entities.

    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
     they
    -1.67
     They
    -1.54
     ossia
    -1.38
    They
    -1.36
     éstas
    -1.32
     为什么
    -1.32
     cokelat
    -1.31
     Рекоменду
    -1.31
     viejas
    -1.31
    лять
    -1.29
    POSITIVE LOGITS
     the
    1.21
    дох
    1.20
     тоже
    1.20
       
    1.16
     too
    1.11
    -
    1.09
     are
    1.09
     also
    1.05
    en
    1.05
    li
    1.03
    Activations Density 0.360%

    No Known Activations