© 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. 34-GEMMASCOPE-RES-131K
    7. 94060
    Prev
    Next
    INDEX
    Explanations

    other way around and vice versa

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

    This neuron detects expressions of inversion or reversal, such as “the other way around” (and similar phrases like “vice versa”).

    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
    ♢
    -0.85
     Vibration
    -0.75
    ategori
    -0.72
    $")
    -0.71
     baix
    -0.69
     foli
    -0.68
    ANGEL
    -0.68
     Pizarro
    -0.68
    HAW
    -0.68
    рода
    -0.68
    POSITIVE LOGITS
     way
    1.20
     around
    1.13
     round
    0.93
    Around
    0.93
     Way
    0.90
     Around
    0.88
    Way
    0.86
     herum
    0.80
     viewer
    0.78
    WAY
    0.77
    Activations Density 0.025%

    No Known Activations