© 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. 10-GEMMASCOPE-RES-131K
    4. 47716
    Prev
    Next
    INDEX
    Explanations

    programming constructs and concepts

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

    The neuron detects programming API/library identifiers and function or method names in code snippets.

    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
     of
    -1.55
     parfü
    -1.33
     lada
    -1.33
     krim
    -1.31
     kamb
    -1.31
     kaos
    -1.31
     velg
    -1.30
     fabrik
    -1.29
     herren
    -1.28
     eenig
    -1.28
    POSITIVE LOGITS
     ακό
    1.57
    𝗠
    1.45
    erializer
    1.41
     sogar
    1.40
     Ainda
    1.39
     limitado
    1.38
    )$.
    1.35
     Aún
    1.34
     introducir
    1.34
     religieux
    1.32
    Activations Density 0.013%

    No Known Activations