© 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. 34-GEMMASCOPE-RES-131K
    7. 98344
    Prev
    Next
    INDEX
    Explanations

    code identifiers and attributes

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

    The neuron is specialized to pick out programming identifiers—especially multi-character names in code such as CamelCase class/type names or ALL_CAPS constants.

    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
     ism
    -0.90
    RAK
    -0.88
     国道
    -0.85
     سرویس
    -0.81
    either
    -0.79
    ジョン
    -0.79
     aufgestellt
    -0.79
     gand
    -0.78
     terrier
    -0.77
     kB
    -0.77
    POSITIVE LOGITS
    宦
    0.85
    Poloha
    0.82
    appare
    0.81
     mér
    0.81
    沿い
    0.81
     نکنید
    0.81
     crece
    0.80
    şap
    0.79
    凄
    0.79
    ']=
    0.78
    Activations Density 0.014%

    No Known Activations