© 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. 130753
    Prev
    Next
    INDEX
    Explanations

    agreement on or with

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

    The neuron fires on occurrences of the word “agreement” (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
    ⎚
    -2.81
    埽
    -2.80
    
    -2.77
    ㍑
    -2.70
    ᥬ
    -2.67
    ╽
    -2.58
    ꜆
    -2.55
    ᕦ
    -2.50
    各样的
    -2.48
     konkret
    -2.45
    POSITIVE LOGITS
    酲
    2.97
    鎗
    2.78
    ⇰
    2.77
    灕
    2.75
     Undoubtedly
    2.58
    最后由
    2.56
     Bedür
    2.48
    欵
    2.48
    凝土
    2.47
    祆
    2.47
    Activations Density 0.006%

    No Known Activations