© 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. 47796
    Prev
    Next
    INDEX
    Explanations

    Bash built-in commands

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

    The neuron flags technical programming and system‐call terms (e.g. shell, SIGCHLD, fork, register, handle, process, exit).

    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
     stay
    -1.46
    stay
    -1.27
    Stay
    -1.13
    STAY
    -1.05
     stays
    -1.03
     STAY
    -0.95
     Stays
    -0.90
     staying
    -0.90
     Stay
    -0.88
     stayed
    -0.84
    POSITIVE LOGITS
     built
    1.34
     builtin
    1.19
     Built
    1.11
    builtins
    1.06
     command
    1.06
    built
    1.05
     execute
    1.02
    CommandType
    0.97
     cd
    0.96
     BUILT
    0.96
    Activations Density 0.018%

    No Known Activations