© 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. 22-GEMMASCOPE-RES-131K
    7. 79570
    Prev
    Next
    INDEX
    Explanations

    symbols and code delimiters

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

    The neuron is picking out numeric literals (numbers) 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_22/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
     usein
    -1.11
     έχουν
    -1.07
    了出去
    -1.03
    🏻‍♀️
    -1.02
    phorus
    -0.99
     among
    -0.98
    정보
    -0.97
     from
    -0.96
     negó
    -0.95
    titutional
    -0.95
    POSITIVE LOGITS
    愉
    0.94
    Debate
    0.88
     الاث
    0.86
     frig
    0.82
    2
    0.82
     Umständen
    0.81
     izd
    0.80
    蟑
    0.80
     vieler
    0.79
    朝着
    0.79
    Activations Density 0.003%

    No Known Activations