© 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. 34-GEMMASCOPE-RES-131K
    7. 56677
    Prev
    Next
    INDEX
    Explanations

    eternal or perpetual

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

    The main thing this neuron does is detect the word “eternal” (in any capitalization) in the text.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     पूरी
    -0.93
     ایک
    -0.93
    所以我
    -0.91
    antry
    -0.91
    icie
    -0.89
    puma
    -0.88
     inggris
    -0.87
     entire
    -0.85
    zyna
    -0.85
    と思って
    -0.84
    POSITIVE LOGITS
    不变
    1.12
     recurrence
    1.05
    lasting
    1.03
     vigilance
    1.02
     sunshine
    0.96
     youth
    0.90
     Sunshine
    0.90
    ummer
    0.89
     forteller
    0.88
     двигатель
    0.87
    Activations Density 0.011%

    No Known Activations