© 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. 75490
    Prev
    Next
    INDEX
    Explanations

    now indicating current status

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

    The neuron detects occurrences of the word “now.”

    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
    1
    -2.78
    6
    -2.69
    0
    -2.64
    3
    -2.58
    \
    -2.58
    8
    -2.55
    7
    -2.44
    4
    -2.41
    "
    -2.33
     it
    -2.31
    POSITIVE LOGITS
    为啥
    2.14
    zmm
    2.03
    って思
    1.96
    冏
    1.92
    褔
    1.88
    と思いました
    1.88
    xnn
    1.87
    
    1.85
    aculture
    1.84
    riculum
    1.84
    Activations Density 0.029%

    No Known Activations