© 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. 22-GEMMASCOPE-RES-131K
    7. 72222
    Prev
    Next
    INDEX
    Explanations

    first come served

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

    The neuron specializes in spotting the ordinal “first” (e.g. in “first-come, first-served” or “first to see”)—i.e. instances of “first” indicating sequence or priority.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     l
    -1.15
      
    -1.08
     \
    -1.07
     Werte
    -1.05
     
    -1.03
    й
    -1.03
     Harmon
    -1.02
       
    -1.02
     Value
    -1.01
     Now
    -0.99
    POSITIVE LOGITS
     those
    1.59
     küm
    1.16
    ądź
    1.15
     after
    1.14
     rempliss
    1.08
    gegeven
    1.03
     whoever
    1.02
    璈
    1.02
     první
    1.02
     masculina
    1.01
    Activations Density 0.008%

    No Known Activations