© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72540
    Prev
    Next
    INDEX
    Explanations

    device paths like /dev/sda

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

    The neuron strongly activates on the numeric token “0” (especially when it appears in device or interface names like drbd0, eth0, ttyACM0).

    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
    Composición
    -1.46
     venons
    -1.45
    ֢
    -1.44
     她
    -1.36
    でしょうね
    -1.33
     podrá
    -1.30
     espesor
    -1.28
    Ainda
    -1.27
     苏
    -1.27
     \%)
    -1.26
    POSITIVE LOGITS
     in
    1.45
    >
    1.41
     then
    1.39
    使用
    1.39
     использованием
    1.38
    ><
    1.37
    *.
    1.34
    ".
    1.34
     =
    1.27
    \
    1.27
    Activations Density 0.077%

    No Known Activations