© 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. 45672
    Prev
    Next
    INDEX
    Explanations

    Excellent as a positive descriptor

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

    The neuron specifically fires on occurrences of the word “Excellent.”

    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
    嫑
    -2.80
    釙
    -2.75
    鹪
    -2.55
    骘
    -2.53
    婊
    -2.52
    皝
    -2.52
     deliciously
    -2.50
     delightfully
    -2.47
    嘖
    -2.45
    驺
    -2.45
    POSITIVE LOGITS
    .
    3.16
    (?)
    2.53
    ,’
    2.41
    Just
    2.41
    There
    2.41
    Even
    2.38
    –
    2.36
    ());
    2.34
    With
    2.33
    You
    2.28
    Activations Density 0.012%

    No Known Activations