© 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. 118056
    Prev
    Next
    INDEX
    Explanations

    command line execution showing output

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

    This neuron activates on command‐line tokens (e.g. shell commands, flags, and pipeline components).

    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
    seys
    -0.81
     popraw
    -0.81
     crée
    -0.79
    vanta
    -0.79
     muut
    -0.78
    taş
    -0.77
    γκ
    -0.77
    ρά
    -0.76
    oler
    -0.75
    ダル
    -0.75
    POSITIVE LOGITS
     output
    1.42
    showAll
    1.34
     grep
    1.25
    输出
    1.22
    output
    1.21
    grep
    1.11
     |
    1.11
    Output
    1.09
     showing
    1.04
     Output
    1.03
    Activations Density 0.075%

    No Known Activations