© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54069
    Prev
    Next
    INDEX
    Explanations

    National followed by noun

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

    The neuron fires most strongly on the capitalized word “National,” e.g. in organizational or publication titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ┣
    -0.71
    放弃
    -0.68
     Fix
    -0.68
    PKG
    -0.67
    ilà
    -0.66
    最大的
    -0.65
     gezet
    -0.65
    ilien
    -0.65
     Cui
    -0.65
    罗斯
    -0.65
    POSITIVE LOGITS
    toLowerCase
    0.76
     Artist
    0.75
     Künstler
    0.74
     artists
    0.72
     reductase
    0.71
    étaires
    0.71
     Septiembre
    0.67
    ニ
    0.66
     UnityEditor
    0.66
     xhr
    0.66
    Activations Density 0.028%

    No Known Activations