© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102452
    Prev
    Next
    INDEX
    Explanations

    replicate, mimic, emulate

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

    The neuron detects words expressing imitation or reproduction (e.g., “replicate,” “replicates,” “mimicked,” “emulating”).

    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
    urazione
    -1.84
    [])
    
    -1.67
    ;}
    
    -1.55
    薷
    -1.52
    //}
    
    -1.50
    //{
    
    -1.50
     نفسها
    -1.48
    渼
    -1.46
    )?;
    -1.45
     nuova
    -1.44
    POSITIVE LOGITS
    x
    1.77
     that
    1.50
     what
    1.44
    {//
    1.40
    //
    1.37
     withstand
    1.34
     réglementation
    1.34
    iskt
    1.34
     imitate
    1.33
     the
    1.32
    Activations Density 0.070%

    No Known Activations