© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    so as to + verb"}

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

    This neuron detects the purpose‐clauses “so as to” (i.e. the “as…to” construction indicating intent).

    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
     hight
    -2.25
    дження
    -1.89
     olduk
    -1.73
     Gedanke
    -1.72
     hella
    -1.70
    //{
    -1.66
    ”，
    -1.64
     तरी
    -1.61
    itées
    -1.60
    ㈣
    -1.59
    POSITIVE LOGITS
    *
    2.22
           
    2.05
              
    2.05
                         
    2.05
            
    1.98
         
    1.98
                      
    1.95
    ?
    1.93
                       
    1.93
        
    1.92
    Activations Density 0.006%

    No Known Activations