© 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. 10-GEMMASCOPE-RES-131K
    7. 23994
    Prev
    Next
    INDEX
    Explanations

    words starting with ge

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

    The neuron is triggered by the subword “ge” (i.e. it fires on any token piece containing the letters “g-e”).

    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
     
    -3.00
    s
    -2.84
    出
    -2.80
    for
    -2.50
     “
    -2.48
    ellido
    -2.45
     of
    -2.39
    
    -2.33
     tetapi
    -2.33
     (“
    -2.30
    POSITIVE LOGITS
    
    2.70
    оргаш
    2.67
     ſch
    2.66
    🧌
    2.58
    馓
    2.56
    água
    2.47
     tarifas
    2.47
    openha
    2.44
     técn
    2.42
    
    2.42
    Activations Density 0.001%

    No Known Activations