© 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. 22-GEMMASCOPE-RES-131K
    4. 13573
    Prev
    Next
    INDEX
    Explanations

    Telerik, Factory, Reporting, Shell, datasource, crystal, Scintilla, Gtk, Spatial, Forms

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

    The neuron fires on library or framework names (vendor/namespace identifiers) in code imports and headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     at
    -1.60
     or
    -1.55
     in
    -1.54
     as
    -1.52
     get
    -1.42
     to
    -1.39
     know
    -1.36
     on
    -1.34
     even
    -1.33
     time
    -1.30
    POSITIVE LOGITS
    を使用して
    1.39
     häufiger
    1.38
     intrigu
    1.27
    臃
    1.20
     dieselben
    1.19
     هنگام
    1.16
     definiert
    1.15
     reinst
    1.13
    蹰
    1.12
    又要
    1.11
    Activations Density 0.001%

    No Known Activations