© 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. 34-GEMMASCOPE-RES-131K
    7. 30646
    Prev
    Next
    INDEX
    Explanations

    comparison

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

    This neuron responds to the stem “compar” (as in compare, comparison, comparative) whenever that token‐fragment appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    comparing
    -0.89
     Couples
    -0.85
     Matching
    -0.84
     هل
    -0.78
     Match
    -0.77
     clashes
    -0.76
     Matches
    -0.76
     relate
    -0.75
     Containers
    -0.75
    whatsapp
    -0.73
    POSITIVE LOGITS
     comparison
    2.83
     comparisons
    2.06
    comparison
    1.80
    Comparison
    1.67
     compar
    1.59
     Comparison
    1.56
    compar
    1.48
     COMPARISON
    1.28
     comparative
    1.24
     Comparisons
    1.23
    Activations Density 0.051%

    No Known Activations