© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82365
    Prev
    Next
    INDEX
    Explanations

    file commands

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

    The neuron is detecting hyphens that introduce command-line options (i.e. flag markers) in shell and package-management commands.

    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
     by
    -1.04
    風味
    -1.02
     other
    -0.99
     might
    -0.97
     in
    -0.94
     appear
    -0.88
     Jüng
    -0.85
     even
    -0.85
     additional
    -0.85
    があり
    -0.84
    POSITIVE LOGITS
    ucie
    0.96
     prezen
    0.92
    urile
    0.91
    verbrauch
    0.90
    spiele
    0.88
     immédiatement
    0.88
     Quiet
    0.88
     gangen
    0.85
    用に
    0.85
    bringen
    0.85
    Activations Density 0.034%

    No Known Activations