© 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. 10-GEMMASCOPE-RES-131K
    7. 58010
    Prev
    Next
    INDEX
    Explanations

    coming to light

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

    The neuron strongly activates on occurrences of the word “light,” especially in contexts like “come to light,” “shed light,” or “into the light” that signal revealing or showing something.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </td>
    -1.53
     As
    -1.52
     I
    -1.52
    [
    -1.48
     Some
    -1.40
     adopté
    -1.40
     anderen
    -1.39
     других
    -1.39
     donde
    -1.38
     are
    -1.36
    POSITIVE LOGITS
    eload
    1.76
    ꪻ
    1.52
    neter
    1.48
    tocks
    1.47
    lük
    1.45
    KJ
    1.45
    showed
    1.41
     necessidades
    1.40
     pomocí
    1.39
    kových
    1.37
    Activations Density 0.029%

    No Known Activations