© 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. 22-GEMMASCOPE-RES-131K
    7. 25635
    Prev
    Next
    INDEX
    Explanations

    sudo followed by system commands

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

    The neuron fires on the use of the “sudo” command (i.e. lines invoking elevated‐privilege operations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ໊
    -2.08
     tačiau
    -1.92
     his
    -1.92
    籐
    -1.88
    荦
    -1.84
     histó
    -1.84
    蛱
    -1.81
     tématu
    -1.79
    鹋
    -1.75
     beiden
    -1.70
    POSITIVE LOGITS
    ed
    1.85
     ,‬
    1.72
     perche
    1.53
    鉭
    1.52
    ↵
    1.51
     accelerating
    1.48
    a
    1.46
    ちゃ
    1.46
    ❉
    1.45
     creativo
    1.45
    Activations Density 0.005%

    No Known Activations