© 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. 104702
    Prev
    Next
    INDEX
    Explanations

    code function definitions

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

    the keyword "fun" in Kotlin function declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of “fun,” i.e. Kotlin function declarations.

    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
     parfü
    -2.95
     parfüm
    -2.92
     abiye
    -2.81
     graisse
    -2.78
    茕
    -2.77
     間取り
    -2.77
    dengan
    -2.72
     möjlighet
    -2.72
     eşofman
    -2.66
     fizik
    -2.66
    POSITIVE LOGITS
     to
    4.72
    z
    2.92
          
    2.75
     R
    2.75
     M
    2.69
     /
    2.67
     D
    2.52
     is
    2.50
     Its
    2.48
              
    2.47
    Activations Density 0.001%

    No Known Activations