© 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. 68433
    Prev
    Next
    INDEX
    Explanations

    font size and style

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

    The neuron fires on numeric tokens (i.e. sequences of digits or numbers).

    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
    bezpiec
    -1.00
     sicherlich
    -0.94
    pdev
    -0.90
     descrição
    -0.90
    genicity
    -0.88
    امة
    -0.88
     solutions
    -0.86
    يدا
    -0.86
    batis
    -0.85
    の説明
    -0.84
    POSITIVE LOGITS
    owulf
    0.92
     аса
    0.88
     даже
    0.85
     menggel
    0.84
     mengangg
    0.83
    νες
    0.82
    έ
    0.82
    Fonto
    0.81
     plass
    0.81
    スマス
    0.81
    Activations Density 0.001%

    No Known Activations