© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8745
    Prev
    Next
    INDEX
    Explanations

    command line package managers

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

    This neuron fires on inline code tokens—especially names of command‐line tools, package files, and programming identifiers.

    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
     which
    -2.19
    !
    -2.05
     proved
    -1.88
     has
    -1.84
     often
    -1.73
     "
    -1.73
     chose
    -1.72
     described
    -1.71
     may
    -1.70
     started
    -1.69
    POSITIVE LOGITS
    </i>
    3.05
     you
    2.08
     抠
    2.05
     aussit
    2.03
     auffi
    2.03
     transacción
    2.02
     these
    1.99
    
    1.98
    ㍑
    1.95
    pendentif
    1.93
    Activations Density 0.091%

    No Known Activations