© 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. 56959
    Prev
    Next
    INDEX
    Explanations

    amazon.com links

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

    The neuron fires strongly on tokens from AWS‐related URLs—e.g. “aws,” “amazon,” and the path segments in “aws.amazon.com/…”—so it’s detecting AWS/Amazon documentation links.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ゼ
    -0.82
     hip
    -0.81
    ZY
    -0.78
    GB
    -0.75
    xas
    -0.75
    Coo
    -0.74
    VertexAttrib
    -0.74
    unku
    -0.74
     Coo
    -0.73
     GB
    -0.72
    POSITIVE LOGITS
     shrew
    0.81
    CLOCK
    0.79
    tellingen
    0.70
     Mahogany
    0.68
    cipital
    0.68
     Esperanza
    0.68
     {:
    0.67
     Agencia
    0.66
    чают
    0.66
    Sabine
    0.64
    Activations Density 0.025%

    No Known Activations