© 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. 105683
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    opening curly braces in code, especially after function or method declarations.

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

    The neuron fires most strongly on opening curly‐brace tokens (the “{” that begins code blocks).

    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
    ご覧
    -1.60
     gardien
    -1.59
    φαλ
    -1.55
     photographe
    -1.52
     catedral
    -1.52
     typu
    -1.48
    gerea
    -1.45
    ܆
    -1.45
     acteur
    -1.41
     collè
    -1.41
    POSITIVE LOGITS
     it
    1.91
           
    1.67
          
    1.58
     according
    1.51
         
    1.48
               
    1.46
             
    1.45
                   
    1.44
     ponieważ
    1.41
     &
    1.41
    Activations Density 0.012%

    No Known Activations