© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72605
    Prev
    Next
    INDEX
    Explanations

    you followed by verbs

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

    This neuron responds strongly to occurrences of the second-person pronoun “you,” especially when addressing or questioning the reader or listener.

    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
    ïti
    -1.61
    葙
    -1.60
     compartilhar
    -1.43
     Töchter
    -1.38
     Surprisingly
    -1.38
    thâu
    -1.36
     bestäm
    -1.30
    zeichnis
    -1.29
    Apenas
    -1.27
    佉
    -1.27
    POSITIVE LOGITS
     then
    1.63
    those
    1.50
    qualität
    1.39
    Then
    1.34
    віч
    1.33
     to
    1.30
    such
    1.28
    then
    1.27
     Référence
    1.27
    these
    1.26
    Activations Density 0.031%

    No Known Activations