© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64521
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

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

    The neuron strongly activates on personal pronouns (e.g. he, she, I, they).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     other
    -1.07
     sobbing
    -1.05
     tertawa
    -1.03
    lara
    -1.01
    以及
    -1.00
    หรือ
    -0.99
     atau
    -0.98
    最初
    -0.97
    جیب
    -0.97
     these
    -0.96
    POSITIVE LOGITS
     then
    1.78
     hadn
    1.30
    Then
    1.27
     had
    1.25
     knew
    1.16
     سپس
    1.15
    then
    1.12
    靱
    1.06
     entonces
    1.03
    ثم
    1.03
    Activations Density 0.004%

    No Known Activations