© 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. 22-GEMMASCOPE-RES-131K
    7. 67666
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    The neuron strongly activates on personal pronouns (e.g. I, you, we, they, it).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.20
     although
    -1.60
    </strong>
    -1.59
     despite
    -1.57
     in
    -1.56
     because
    -1.52
     before
    -1.52
     while
    -1.47
     after
    -1.46
     until
    -1.45
    POSITIVE LOGITS
     It
    1.84
    久し
    1.77
    遠く
    1.65
     I
    1.64
     sorteo
    1.62
     attribué
    1.58
     llavero
    1.53
     bietet
    1.52
    へ向
    1.51
     offre
    1.50
    Activations Density 0.127%

    No Known Activations