© 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. 10-GEMMASCOPE-RES-131K
    7. 43424
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

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

    This neuron activates on third-person references—pronouns (he, she, they, their, itself, etc.) and similar entity mentions.

    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
    </b>
    -1.46
    iecie
    -1.23
    IOR
    -1.23
    ("")]
    -1.21
    ">
    -1.20
    ):
    -1.20
    untamiento
    -1.20
    рений
    -1.20
    cirq
    -1.20
     now
    -1.19
    POSITIVE LOGITS
    -
    1.38
     Contenido
    1.30
    わん
    1.23
    gı
    1.23
    してくれた
    1.20
     kimdir
    1.19
     schilder
    1.18
    ,
    1.16
     birbir
    1.16
     themselves
    1.16
    Activations Density 0.341%

    No Known Activations