© 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. 10-GEMMASCOPE-RES-131K
    7. 105889
    Prev
    Next
    INDEX
    Explanations

    fileName, BufferedImage, product, design

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

    the neuron detects programming identifiers (e.g. variable, class, or method names) in 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_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
    ”;
    -2.48
     wth
    -2.44
            
    -2.44
    ons
    -2.33
    ↵↵
    -2.27
    ach
    -2.16
     et
    -2.16
     kteří
    -2.13
    而在
    -2.13
    经常
    -2.09
    POSITIVE LOGITS
    
    2.59
    zość
    2.55
    を見て
    2.52
    laştır
    2.44
    жена
    2.38
     exé
    2.27
    )
    2.27
     puisse
    2.27
    }
    2.27
    ของ
    2.23
    Activations Density 0.003%

    No Known Activations