© 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. 56887
    Prev
    Next
    INDEX
    Explanations

    Bay Area and local area networks

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

    The neuron detects occurrences of the word “area” (e.g. in “Bay Area,” “local area,” “wide area,” etc.).

    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
     ECR
    -0.81
     Crouch
    -0.72
    pote
    -0.70
     distort
    -0.69
     kwiet
    -0.68
    Tah
    -0.67
     волос
    -0.67
    トリック
    -0.67
    issy
    -0.66
     раск
    -0.66
    POSITIVE LOGITS
     area
    3.02
     Area
    2.92
    Area
    2.89
     AREA
    2.61
    area
    2.56
    AREA
    2.56
     área
    1.96
     Área
    1.66
    Área
    1.52
    エリア
    1.40
    Activations Density 0.029%

    No Known Activations