© 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. 33300
    Prev
    Next
    INDEX
    Explanations

    child birth order

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

    The neuron flags ordinal birth‐order phrases (e.g. “third of three children,” “fourth of six children”).

    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
     for
    -0.99
     bereits
    -0.93
     or
    -0.93
     During
    -0.91
    ύπ
    -0.90
     Cedex
    -0.90
                       
    -0.87
     For
    -0.86
    neming
    -0.86
                    
    -0.85
    POSITIVE LOGITS
     harap
    1.05
     vélos
    1.05
     appareils
    1.04
    generally
    1.02
     algu
    1.00
     cinq
    0.98
     velké
    0.96
    ImageName
    0.95
     combien
    0.95
    litten
    0.94
    Activations Density 0.012%

    No Known Activations