© 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. 34-GEMMASCOPE-RES-131K
    4. 87136
    Prev
    Next
    INDEX
    Explanations

    assembly attributes or XAML names

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

    This neuron detects programming identifiers, especially PascalCase type or namespace names in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     both
    -1.23
     in
    -1.16
     only
    -1.05
     just
    -1.05
     out
    -1.03
     although
    -1.00
     without
    -0.99
     but
    -0.97
     comes
    -0.97
     through
    -0.96
    POSITIVE LOGITS
     probablement
    1.08
     AMAZING
    1.07
     trám
    1.03
     hahaha
    0.99
     Herbs
    0.98
    pflege
    0.95
     ſer
    0.95
     SNES
    0.94
     ГУ
    0.94
    hope
    0.93
    Activations Density 0.001%

    No Known Activations