© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58594
    Prev
    Next
    INDEX
    Explanations

    Quick Overview, Daniel Radcliffe, Sar casm

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

    This neuron detects numeric literals (both integers and floating‐point numbers) in code snippets.

    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
    xvii
    -1.95
     constantemente
    -1.80
     neumáticos
    -1.75
     they
    -1.73
     recentemente
    -1.70
     моей
    -1.67
     zoude
    -1.66
    茕
    -1.63
     claramente
    -1.63
    xvi
    -1.62
    POSITIVE LOGITS
    年は
    2.02
     in
    1.93
    年には
    1.77
    の詳細
    1.77
    ！】
    1.70
    年も
    1.66
    旰
    1.65
     ۱۷
    1.62
     If
    1.54
     also
    1.53
    Activations Density 0.008%

    No Known Activations