© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100331
    Prev
    Next
    INDEX
    Explanations

    Chinese place names, technology, food, locations

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

    This neuron activates on mentions of “端” (the Chinese character for “terminal/endpoint”) and its English equivalent “terminal,” i.e. references to endpoints or terminals.

    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
    ↵
    -3.02
    .
    -2.77
     Hinblick
    -2.55
     Verständ
    -2.22
     his
    -2.19
     It
    -2.13
     That
    -2.13
     vorigen
    -2.08
     Also
    -2.06
     The
    -2.03
    POSITIVE LOGITS
    
    2.66
    荜
    2.53
    ଃ
    2.50
    逦
    2.36
    缬
    2.31
     optimise
    2.27
    主的
    2.27
    鈊
    2.25
    橼
    2.22
    इटम
    2.20
    Activations Density 0.001%

    No Known Activations