© 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. 10-GEMMASCOPE-RES-131K
    7. 7812
    Prev
    Next
    INDEX
    Explanations

    commands and related phrases

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

    The neuron fires on code identifiers and import names containing the word “Command,” i.e. references to command‐related classes, functions, or modules.

    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
     Often
    -1.48
     ventre
    -1.34
     vehemently
    -1.33
     Providing
    -1.31
    Often
    -1.30
     Sometimes
    -1.30
     troubling
    -1.29
    Through
    -1.28
    Sometimes
    -1.27
     Typically
    -1.27
    POSITIVE LOGITS
     to
    1.73
    ֟
    1.59
     amazingly
    1.52
     felicitación
    1.52
            
    1.50
     crucial
    1.50
    
    1.48
     a
    1.48
                
    1.47
    駡
    1.45
    Activations Density 0.012%

    No Known Activations