© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112978
    Prev
    Next
    INDEX
    Explanations

    vice versa

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

    The main thing this neuron does is detect the phrase “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_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
     in
    -2.08
     of
    -2.05
    ꦤ
    -2.03
    }>
    
    -1.80
     and
    -1.74
    %;">
    -1.70
    杮
    -1.65
    鵪
    -1.63
    掄
    -1.62
    鴣
    -1.62
    POSITIVE LOGITS
    The
    2.02
     zoude
    1.85
     dibanding
    1.84
     essais
    1.74
    it
    1.73
     timmar
    1.73
    It
    1.71
    b
    1.68
     améliorer
    1.66
     construire
    1.66
    Activations Density 0.002%

    No Known Activations