© 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. 24993
    Prev
    Next
    INDEX
    Explanations

    Selector, CR, strings, Download, Mongo, Win, Oracle

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

    This neuron fires on named entities and acronyms (e.g. brand names, section headings, uppercase alphanumeric tokens).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     senhor
    -0.99
     irmão
    -0.98
     schlaf
    -0.93
     limón
    -0.93
     papai
    -0.93
    AIzaSy
    -0.93
     menino
    -0.92
    λους
    -0.91
     trö
    -0.91
    𝚑
    -0.90
    POSITIVE LOGITS
    ｒ
    0.92
     theologian
    0.89
     ملابس
    0.85
     delinqu
    0.79
    OrEmpty
    0.79
    엣
    0.79
     оста
    0.78
     Ral
    0.78
    ivano
    0.77
     sociologist
    0.77
    Activations Density 0.145%

    No Known Activations