© 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. 47838
    Prev
    Next
    INDEX
    Explanations

    javascript, java, and c# keywords

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

    The neuron is strongly triggered by the “.” token when used as a separator in fully qualified names or member-access expressions 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
    Also
    -2.06
    If
    -1.98
    There
    -1.97
    One
    -1.91
    For
    -1.80
    At
    -1.76
    All
    -1.73
    Two
    -1.68
    _{
    -1.68
     також
    -1.67
    POSITIVE LOGITS
     frequentemente
    1.84
     praticamente
    1.74
     pozdě
    1.70
     Antwort
    1.59
     nhưng
    1.56
     แต่
    1.56
     pensamos
    1.55
     its
    1.54
     certamente
    1.54
    
    1.52
    Activations Density 0.006%

    No Known Activations