© 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. 22-GEMMASCOPE-RES-131K
    7. 34150
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

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

    The neuron is detecting standalone numeric tokens (numbers and numeric literals) in the text.

    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
    或
    -1.09
    或者
    -1.04
     or
    -1.01
     sorteo
    -0.98
     dubbio
    -0.95
    тивний
    -0.95
    ajā
    -0.94
    ♜
    -0.91
     knowledge
    -0.91
     zeggen
    -0.91
    POSITIVE LOGITS
     two
    1.02
     คือ
    0.88
     faç
    0.83
    boxing
    0.82
    
    0.78
    щина
    0.78
    笑意
    0.78
     Colombie
    0.77
    Cou
    0.76
     sprawia
    0.76
    Activations Density 0.003%

    No Known Activations