© 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. 66059
    Prev
    Next
    INDEX
    Explanations

    UI methods and lifecycle

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

    This neuron detects code tokens corresponding to method or function names (e.g., CamelCase identifiers like onCreateOptionsMenu, touchesBegan, drawRect, etc.).

    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
     první
    -1.58
    𝑯
    -1.55
     $
    -1.44
     pretende
    -1.43
    often
    -1.41
     concepción
    -1.38
    paravant
    -1.38
     first
    -1.37
     regresa
    -1.36
    ке
    -1.35
    POSITIVE LOGITS
     sposob
    1.63
    2
    1.56
     libremente
    1.45
    0
    1.45
    Děkuji
    1.41
    Also
    1.34
     ryb
    1.34
     okno
    1.32
    Podob
    1.31
    チューム
    1.30
    Activations Density 0.018%

    No Known Activations