© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15594
    Prev
    Next
    INDEX
    Explanations

    explaining origins of a name

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

    This neuron detects contexts that explain a name’s origin or meaning (e.g., “gets its name from,” “named because,” “which means”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    この日は
    -1.28
    what
    -1.27
    飈
    -1.26
     renovables
    -1.26
     (!_
    -1.25
    ærke
    -1.23
    Camila
    -1.23
    tización
    -1.23
     who
    -1.22
    eynman
    -1.22
    POSITIVE LOGITS
    驺
    1.66
    ("")
    1.48
    眛
    1.45
     美丽
    1.38
    "")
    1.38
    饧
    1.36
    豨
    1.33
     לאחר
    1.33
    
    1.32
    =’
    1.31
    Activations Density 0.047%

    No Known Activations