© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43333
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    The neuron activates on numeric expressions (digits, spelled‐out numbers, percentages, measurements, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     preocupado
    -1.62
    ”？
    -1.60
    ATUM
    -1.59
    鸰
    -1.52
    ICING
    -1.52
     déterminé
    -1.48
     The
    -1.48
    ೢ
    -1.48
    </h4>
    -1.47
    ᐡ
    -1.46
    POSITIVE LOGITS
    -
    1.50
    
    1.48
     весьма
    1.43
    アレル
    1.42
    In
    1.38
     oignon
    1.37
     zelfs
    1.34
     envelop
    1.34
    The
    1.34
    Originally
    1.31
    Activations Density 0.008%

    No Known Activations