© 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. 71262
    Prev
    Next
    INDEX
    Explanations

    equity and following terms

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

    This neuron detects occurrences of the word “equity” (and its close variants) in the text.

    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
     –
    -3.42
     Of
    -3.28
    真的是
    -3.08
    if
    -2.94
                    
    -2.94
     he
    -2.89
        
    -2.88
    ar
    -2.84
    of
    -2.81
     But
    -2.81
    POSITIVE LOGITS
    𖥦
    3.42
    ープン
    3.30
    渽
    3.06
     bús
    3.00
    牁
    2.95
    𖡼
    2.81
    蠱
    2.78
    ᐡ
    2.73
    趼
    2.70
    訛
    2.67
    Activations Density 0.003%

    No Known Activations