© 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. 22-GEMMASCOPE-RES-131K
    7. 36577
    Prev
    Next
    INDEX
    Explanations

    programming language constructs for lists or arrays

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

    The neuron activates on numeric tokens—digits, numeric literals, array-size brackets, and other number-related code elements.

    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
     Tropfen
    -1.20
     klienta
    -1.06
     or
    -1.04
     Geruch
    -1.02
    TypedValue
    -1.01
     dinosaurio
    -0.99
     itself
    -0.98
     znajdziesz
    -0.94
     Wachstum
    -0.91
    PopupMenu
    -0.91
    POSITIVE LOGITS
    each
    0.93
     각
    0.93
    各个
    0.92
     initComponents
    0.91
     importante
    0.91
     all
    0.90
     đều
    0.90
    forEach
    0.88
     erreichbar
    0.87
     redus
    0.87
    Activations Density 0.009%

    No Known Activations