© 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. 79374
    Prev
    Next
    INDEX
    Explanations

    county budget

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

    The neuron is detecting numeric tokens—especially years, dollar amounts, and other figures—in budget‐related contexts.

    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
    Notices
    -0.71
     έχ
    -0.71
    储存
    -0.70
     Rosales
    -0.69
     मा
    -0.68
     compacta
    -0.68
     cerámica
    -0.68
     alternately
    -0.67
    をします
    -0.66
     release
    -0.66
    POSITIVE LOGITS
    Fund
    1.12
    GENERAL
    1.11
     General
    1.05
     general
    1.05
    General
    1.05
     Fund
    1.02
    fund
    0.94
     fund
    0.93
     enterprise
    0.93
     général
    0.89
    Activations Density 0.015%

    No Known Activations