© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100366
    Prev
    Next
    INDEX
    Explanations

    verbs followed by determiners or prepositions

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

    The neuron fires on dynamic process‐describing verbs—especially third‐person singular present‐tense action verbs that signal ongoing or causal changes (e.g. keeps, leads, occurs, combines).

    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
                          
    -1.76
                       
    -1.73
                            
    -1.72
                   
    -1.70
                         
    -1.66
                           
    -1.63
                  
    -1.63
                 
    -1.60
                      
    -1.56
               
    -1.54
    POSITIVE LOGITS
     также
    1.77
     their
    1.75
     також
    1.48
     the
    1.45
    Также
    1.42
     or
    1.38
     that
    1.38
    neue
    1.35
    ských
    1.35
     '?
    1.35
    Activations Density 0.450%

    No Known Activations