© 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. 127926
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on specialized technical or domain‐specific jargon terms indicating distinct subject‐matter contexts.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    requires

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Spani
    -1.00
     CHAIRMAN
    -0.95
     ними
    -0.95
    жливо
    -0.88
     结果
    -0.88
     PROVIDED
    -0.87
     菜单
    -0.87
     APPELL
    -0.87
     pourront
    -0.86
     POWERS
    -0.85
    POSITIVE LOGITS
     requires
    2.45
     require
    2.33
     requiring
    1.99
     requirements
    1.87
     required
    1.75
    Requires
    1.73
    requires
    1.65
    require
    1.64
     requirement
    1.63
     wymaga
    1.60
    Activations Density 0.168%

    No Known Activations