© 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. 67160
    Prev
    Next
    INDEX
    Explanations

    numbers followed by closing parentheses

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

    The neuron detects reported statistical result numbers, especially p-values and related test statistics in scientific 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_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
    蓠
    -1.91
     tranſ
    -1.84
    蟜
    -1.80
    
    -1.77
     nombrado
    -1.77
    跸
    -1.74
     nasıl
    -1.71
    翆
    -1.69
    ⎔
    -1.67
    
    -1.66
    POSITIVE LOGITS
    4
    2.45
    1
    2.31
    2
    2.19
    5
    2.08
    8
    2.03
    This
    1.80
    3
    1.78
     only
    1.70
     for
    1.66
    9
    1.62
    Activations Density 0.020%

    No Known Activations