© 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. 84667
    Prev
    Next
    INDEX
    Explanations

    pronouns and their actions

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

    This neuron detects common subject pronouns (particularly “it” and “we”) when they appear as the grammatical subject of a clause.

    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
    “
    -2.41
    While
    -2.09
    You
    -2.06
     “
    -1.86
    Although
    -1.80
    If
    -1.80
    Are
    -1.77
    Why
    -1.75
    What
    -1.74
    、“
    -1.73
    POSITIVE LOGITS
     for
    2.33
     then
    2.17
     about
    1.98
     便利
    1.98
    Kenapa
    1.92
     actually
    1.84
     müssen
    1.73
     explaining
    1.65
    ){
    1.63
     needing
    1.63
    Activations Density 0.015%

    No Known Activations