© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77643
    Prev
    Next
    INDEX
    Explanations

    Go programming language syntax

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

    The neuron fires on Go code block syntax, spotting control‐flow keywords (like “if” and “defer”), braces and their associated indentation.

    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
    Rocky
    -0.83
     movimenti
    -0.78
    csak
    -0.77
    Opciones
    -0.77
     dreaded
    -0.76
     Burgess
    -0.75
    鈴
    -0.75
    常用的
    -0.74
     Restricted
    -0.73
     Rocky
    -0.73
    POSITIVE LOGITS
     err
    0.80
    DateField
    0.79
     Carrasco
    0.77
     hinzufügen
    0.76
     require
    0.76
    防火
    0.75
     peach
    0.75
    charpe
    0.75
    Cursor
    0.74
    烬
    0.74
    Activations Density 0.003%

    No Known Activations