© 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. 73878
    Prev
    Next
    INDEX
    Explanations

    UI layout and list components

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

    The neuron consistently lights up on numeric tokens (digits and numbers) in code and markup.

    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
    anglicky
    -0.96
    Lịch
    -0.96
     Những
    -0.96
    casal
    -0.94
     Spanish
    -0.91
    arsenal
    -0.91
     damaligen
    -0.90
     campaign
    -0.90
     terjadi
    -0.89
     forehead
    -0.88
    POSITIVE LOGITS
    Till
    0.96
     النساء
    0.90
    quete
    0.85
    罗
    0.85
    Sw
    0.85
    Ƀ
    0.84
     componente
    0.84
    Sp
    0.84
    🍯
    0.84
    羅
    0.83
    Activations Density 0.008%

    No Known Activations