© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118713
    Prev
    Next
    INDEX
    Explanations

    NFL practice and players

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

    The neuron selectively activates on numeric tokens and expressions—especially standalone numbers, dates, and other digit‐based sequences.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     recarg
    -0.70
    Butterfly
    -0.66
     espesor
    -0.66
    裨
    -0.66
    ᵍ
    -0.65
    ਔ
    -0.64
    siana
    -0.64
     EMPLOYMENT
    -0.64
     circulation
    -0.63
     ibiza
    -0.63
    POSITIVE LOGITS
     practice
    1.37
     Practice
    1.20
    Practice
    1.13
    practice
    1.06
     Elevation
    1.00
     active
    0.95
     PRACTICE
    0.90
     elevate
    0.90
    PRACTICE
    0.87
     elevated
    0.86
    Activations Density 0.031%

    No Known Activations