© 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. 210
    Prev
    Next
    INDEX
    Explanations

    IV-TR, TR, N-2004KX, const

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

    The neuron consistently fires on standalone numbers and numeric tokens (e.g. years, measurements, model or strain identifiers).

    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
     entdeckt
    -0.94
     réessayer
    -0.89
    uploadFile
    -0.87
     decorativo
    -0.85
    dö
    -0.83
    Sudoku
    -0.82
    gelopen
    -0.81
     образу
    -0.81
     جات
    -0.80
    enetrable
    -0.80
    POSITIVE LOGITS
     with
    1.23
     II
    0.90
    ttps
    0.83
    Plus
    0.82
    หน้าน
    0.82
    但在
    0.81
    alucía
    0.81
     岁
    0.80
    勝負
    0.79
     يق
    0.79
    Activations Density 0.206%

    No Known Activations