© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75547
    Prev
    Next
    INDEX
    Explanations

    carrier testing, aggregation, device, mediated

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

    The neuron detects the term "carrier" when used in technical, scientific, or communications contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     regrets
    -0.91
     regret
    -0.83
     mancher
    -0.82
    Colorful
    -0.81
     champion
    -0.77
    Kontra
    -0.77
    margin
    -0.77
    ло
    -0.75
     Startseite
    -0.74
    lowing
    -0.73
    POSITIVE LOGITS
     carrier
    1.68
     Carrier
    1.62
     carriers
    1.54
    carrier
    1.52
     Carriers
    1.41
    Carrier
    1.38
     pigeons
    1.12
     Carry
    1.10
     Carrying
    1.05
    Carry
    0.99
    Activations Density 0.019%

    No Known Activations