© 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. 34-GEMMASCOPE-RES-131K
    7. 60423
    Prev
    Next
    INDEX
    Explanations

    entered into agreements

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

    The neuron detects occurrences of the verb “enter” (in forms like enters/entered) typically followed by “into,” as in announcing that one party has entered into an agreement or contract.

    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
     WELLS
    -0.71
    ädigung
    -0.71
     obje
    -0.69
     Differences
    -0.69
     цветов
    -0.68
    flows
    -0.68
     CGPoint
    -0.68
    باع
    -0.68
    وقع
    -0.67
     欣赏
    -0.67
    POSITIVE LOGITS
     entered
    2.86
    entered
    2.52
     enter
    2.52
     entering
    2.36
    Entered
    2.28
     enters
    2.23
     Entered
    2.22
     Enter
    2.22
    Enter
    2.17
     ENTER
    2.13
    Activations Density 0.030%

    No Known Activations