© 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. 71491
    Prev
    Next
    INDEX
    Explanations

    his her their him before noun

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

    The neuron strongly activates on third‐person personal and possessive pronouns (e.g. him, her, their, them, his, etc.).

    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
    ,
    -1.33
     llorar
    -1.26
    více
    -1.21
     adequado
    -1.18
    Shou
    -1.17
     verdaderas
    -1.16
     through
    -1.14
    magini
    -1.13
     Through
    -1.11
    锄
    -1.10
    POSITIVE LOGITS
     its
    1.52
    1.13
    1.11
    riad
    1.10
    licopter
    1.08
    finally
    1.08
     kinerja
    1.08
    回数
    1.05
    hopefully
    1.05
    このように
    1.04
    Activations Density 0.104%

    No Known Activations