© 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. 98662
    Prev
    Next
    INDEX
    Explanations

    review or reviewed

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

    The neuron specifically fires on the word “review” (in any context as noun or verb).

    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
     Mainly
    -2.03
     Thus
    -2.02
     Such
    -1.94
     Technically
    -1.94
     Aunque
    -1.89
     ___________
    -1.84
     Incluye
    -1.84
     desenvolvimento
    -1.84
     quizá
    -1.83
     piccole
    -1.80
    POSITIVE LOGITS
     if
    2.13
     it
    2.08
     how
    1.90
     or
    1.85
     in
    1.74
    ၅
    1.68
     decoradas
    1.66
     all
    1.61
     สวย
    1.61
    第五
    1.59
    Activations Density 0.012%

    No Known Activations