© 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. 93062
    Prev
    Next
    INDEX
    Explanations

    programming attributes or keys

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

    The neuron fires on numeric literal values (especially larger numbers) assigned to attributes or parameters in code/XML.

    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
     you
    -1.37
     their
    -1.27
     explique
    -1.18
     your
    -1.09
     have
    -1.08
     bereits
    -1.03
     уже
    -1.01
     indique
    -0.96
    已经
    -0.95
    satunya
    -0.94
    POSITIVE LOGITS
    owels
    1.18
     acolo
    1.12
    Redo
    1.10
    唏
    1.09
    Mundo
    1.09
     المنطقة
    1.09
    Yeni
    1.08
     actualizada
    1.08
    örande
    1.06
    かで
    1.05
    Activations Density 0.004%

    No Known Activations