© 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. 10-GEMMASCOPE-RES-131K
    7. 105479
    Prev
    Next
    INDEX
    Explanations

    `get` followed by `Controller`, `Layout`, `ServiceManager`, `PageTitle`, `Renderer`

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

    object property or array access syntax in programming code, particularly using brackets and dots for method chaining.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on snippets of source code that look like method or property accessors—i.e. CamelCase identifiers used in code (e.g. getAction, getBlock, Rows[…].Cells[…], etc.).

    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
     but
    -1.89
    -1.63
                
    -1.50
     intentando
    -1.38
                  
    -1.33
    MAXN
    -1.32
     diciendo
    -1.29
     ♥
    -1.27
     dejando
    -1.27
    quarelle
    -1.27
    POSITIVE LOGITS
     véritables
    1.59
     lavanda
    1.55
     drau
    1.53
     pascua
    1.51
     conster
    1.48
     impone
    1.45
     felpa
    1.45
     många
    1.43
     multiuso
    1.42
     decorativa
    1.41
    Activations Density 0.009%

    No Known Activations