© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93003
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and structures

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

    The neuron fires on programming‐language declaration or definition keywords—e.g. “public,” “override,” “uniform,” “#include/define,” function signatures, class or namespace declarations, and similar.

    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
     bénéficiaire
    -0.98
    內容簡介
    -0.94
     quatrième
    -0.94
     hâte
    -0.93
     réussite
    -0.90
     MÁS
    -0.90
     récon
    -0.90
     démission
    -0.89
     tives
    -0.89
    鏃
    -0.88
    POSITIVE LOGITS
     GameObject
    1.44
     Transform
    1.37
    Transform
    1.32
     float
    1.26
    Text
    1.17
     transform
    1.17
    Layer
    1.16
     Layer
    1.15
    static
    1.06
    float
    1.03
    Activations Density 0.002%

    No Known Activations