© 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. 117920
    Prev
    Next
    INDEX
    Explanations

    newness and introduction

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

    The neuron primarily detects occurrences of the word “new.”

    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
    <bos>
    -1.09
      
    -1.02
     former
    -1.02
    -
    -1.00
    多年的
    -0.97
    过去了
    -0.95
    )
    -0.91
    浪费
    -0.90
     famoso
    -0.90
    過ぎて
    -0.90
    POSITIVE LOGITS
    sprint
    1.95
    fang
    1.87
    sworth
    1.84
     arrivals
    1.80
     zealand
    1.50
     york
    1.47
     entrants
    1.45
     additions
    1.41
     recruits
    1.41
    tons
    1.36
    Activations Density 0.044%

    No Known Activations