© 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. 98824
    Prev
    Next
    INDEX
    Explanations

    country/region/organization initialisms

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

    The neuron activates on sequences of uppercase letters forming acronyms or initialisms (e.g., organization or country abbreviations).

    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
    Продам
    -1.52
     tristes
    -1.48
    osovo
    -1.46
     from
    -1.46
    Chandigarh
    -1.45
     editados
    -1.44
    豺
    -1.44
    𓍊
    -1.41
    {*}
    -1.41
     komunikasi
    -1.41
    POSITIVE LOGITS
     trofeo
    1.38
    可不是
    1.38
     dalamnya
    1.33
     its
    1.29
    Its
    1.28
    捅
    1.20
    迨
    1.19
    OS
    1.16
    怼
    1.16
    人員
    1.16
    Activations Density 0.070%

    No Known Activations