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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85424
    Prev
    Next
    INDEX
    Explanations

    transport

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

    the word "Transport" in technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of the technical term “transport” (e.g. in code identifiers or protocol names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ㍑
    -2.14
     dà
    -2.08
     dieser
    -2.05
    2
    -2.03
    饪
    -2.02
    ⢊
    -2.02
    栊
    -1.91
     peo
    -1.86
    跟
    -1.84
    ㌘
    -1.84
    POSITIVE LOGITS
    逦
    2.20
    𝘨
    2.02
    ↵
    1.95
    icoot
    1.94
    ).
    1.94
     sassy
    1.93
    皞
    1.92
     multitude
    1.91
     For
    1.84
    城主
    1.84
    Activations Density 0.011%

    No Known Activations