© 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. 62483
    Prev
    Next
    INDEX
    Explanations

    Reuters US news location

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

    This neuron detects the standard wire‐service metadata tokens and formatting (e.g. “Reuters,” dateline parentheses, hyphens, bylines, and related document headers).

    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
     arterio
    -0.88
     bleiben
    -0.77
    └──
    -0.75
    azgo
    -0.75
    てて
    -0.74
     hommes
    -0.74
     établissement
    -0.73
    学家
    -0.73
     syner
    -0.71
    𝓙
    -0.71
    POSITIVE LOGITS
     προ
    0.83
     xxiii
    0.81
    bbing
    0.80
     US
    0.79
    metre
    0.79
     afs
    0.79
    US
    0.77
     Grammy
    0.77
     Toronto
    0.76
    Reuters
    0.76
    Activations Density 0.035%

    No Known Activations