© 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. 34-GEMMASCOPE-RES-131K
    7. 38702
    Prev
    Next
    INDEX
    Explanations

    flag and associated descriptors

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

    The neuron is detecting numeric tokens (strings of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    書いた
    -1.02
    詫
    -0.96
     vast
    -0.96
     staunch
    -0.95
     However
    -0.94
     ogran
    -0.93
     crippling
    -0.91
    nungen
    -0.90
    他会
    -0.90
    当たる
    -0.88
    POSITIVE LOGITS
    flag
    2.30
     flag
    2.11
     Flag
    2.09
     flags
    1.94
     FLAG
    1.84
    Flag
    1.80
     Flags
    1.80
     фла
    1.78
    Flags
    1.69
    FLAG
    1.62
    Activations Density 0.016%

    No Known Activations