© 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. 34-GEMMASCOPE-RES-131K
    7. 57869
    Prev
    Next
    INDEX
    Explanations

    command-line utilities

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

    The neuron is keyed to bits of shell‐oriented code (command names, flags, package/tool names, shebangs, etc.), i.e. tokens you’d see in CLI install or configuration snippets.

    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
    Adult
    -0.75
    正如
    -0.72
    aconda
    -0.71
     prá
    -0.71
     COM
    -0.70
    JsonHelper
    -0.70
     Adult
    -0.69
    travis
    -0.69
    //
    -0.69
     CFD
    -0.68
    POSITIVE LOGITS
     nc
    0.85
     TERM
    0.79
     curses
    0.76
    栄養
    0.76
    Nc
    0.75
    tigos
    0.73
    EIA
    0.73
    Cairo
    0.73
     term
    0.73
    tten
    0.73
    Activations Density 0.213%

    No Known Activations