© 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. 70485
    Prev
    Next
    INDEX
    Explanations

    data density

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

    This neuron fires on tokens that are part of a function’s signature—specifically parameter names, their types, and the return type in declarations.

    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
     이야
    -1.12
     dunklen
    -1.11
     historischen
    -1.02
     erfolgreichen
    -1.00
     erweiterten
    -0.93
     Anleitung
    -0.93
    遑
    -0.93
    limard
    -0.92
     gewerb
    -0.91
     yes
    -0.91
    POSITIVE LOGITS
     verle
    1.03
    データ
    0.95
     Agosto
    0.94
    Cream
    0.88
     vasco
    0.87
    🛎
    0.86
     suporta
    0.86
    数据
    0.85
    着脸
    0.85
    تو
    0.84
    Activations Density 0.005%

    No Known Activations