© 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. 69830
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

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

    The neuron detects numeric literals (numbers or numeric constants) in code.

    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
     is
    -2.14
     will
    -1.97
     can
    -1.91
     only
    -1.90
     even
    -1.88
     if
    -1.80
     would
    -1.77
     in
    -1.74
     and
    -1.73
     should
    -1.69
    POSITIVE LOGITS
    妧
    1.92
    無料で
    1.85
    represents
    1.78
     hinders
    1.75
    ՚
    1.74
    unfortunately
    1.74
     polska
    1.72
    
    1.72
    presumably
    1.70
     excesso
    1.70
    Activations Density 0.005%

    No Known Activations