© 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. 124014
    Prev
    Next
    INDEX
    Explanations

    exceptionally, remarkably, unbelievably

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

    The neuron fires on individual identifier tokens (like variable or parameter names) in code snippets.

    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
     if
    -2.77
     and
    -2.64
     or
    -2.52
     after
    -2.45
     in
    -2.05
     as
    -2.02
     has
    -2.02
     at
    -1.96
     before
    -1.85
     first
    -1.84
    POSITIVE LOGITS
     ridiculously
    2.14
     strikingly
    2.05
     remarkably
    2.03
     unbelievably
    1.91
     insanely
    1.90
     exceptionally
    1.85
     soooo
    1.83
    
    1.81
     tiveram
    1.81
     engraçado
    1.80
    Activations Density 0.049%

    No Known Activations