© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98795
    Prev
    Next
    INDEX
    Explanations

    bash scripts and shell commands

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

    The neuron is detecting Bash‐script boilerplate and strict‐mode directives (e.g. the shebang line plus “set –eu –o pipefail,” IFS assignments, sourcing, etc.).

    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
    phinx
    -0.76
     SIR
    -0.75
    Griff
    -0.68
    SIR
    -0.68
     basketball
    -0.68
     NAN
    -0.66
     python
    -0.66
     depolar
    -0.65
    asyon
    -0.65
     canary
    -0.63
    POSITIVE LOGITS
     bash
    1.34
     shell
    1.31
     Bash
    1.25
     Bourne
    1.22
     Shell
    1.20
     shells
    1.19
    Bash
    1.16
    Shell
    1.13
     script
    1.11
    bash
    1.10
    Activations Density 0.149%

    No Known Activations