© 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. 39099
    Prev
    Next
    INDEX
    Explanations

    on the other hand

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

    The neuron fires on the contrastive connective “on the other hand.”

    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
    i
    -2.52
    a
    -2.23
     on
    -2.00
     seven
    -1.87
     three
    -1.84
    S
    -1.80
     sixty
    -1.78
     twenty
    -1.78
     four
    -1.77
     thirty
    -1.77
    POSITIVE LOGITS
    ܜ
    2.14
     konkrete
    2.08
     superfí
    1.95
     ultimi
    1.94
     ordini
    1.91
     ausdrück
    1.87
     soste
    1.87
     Atención
    1.87
     komplette
    1.87
     attacco
    1.82
    Activations Density 0.010%

    No Known Activations