© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110700
    Prev
    Next
    INDEX
    Explanations

    an adjective or noun

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

    This neuron detects the phrase “has a” indicating possession or attributes (e.g. “Sony has a …,” “ALL VP has a …,” etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ﮨ
    -2.33
    鸶
    -2.19
    鹛
    -1.96
    奩
    -1.96
    𝄇
    -1.93
    
    -1.90
    壠
    -1.90
    ÑOS
    -1.90
    論
    -1.89
    緜
    -1.88
    POSITIVE LOGITS
     been
    2.16
     
    1.93
     {
    1.93
     AND
    1.91
     tendency
    1.81
    縞
    1.81
     （
    1.80
     türlü
    1.79
     और
    1.73
    huge
    1.73
    Activations Density 0.087%

    No Known Activations