© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43709
    Prev
    Next
    INDEX
    Explanations

    alternatives joined by or

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

    The main thing this neuron does is detect occurrences of the conjunction “or.”

    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
    thodox
    -2.91
    馐
    -2.75
    теров
    -2.73
    thodon
    -2.70
    
    -2.66
    鸶
    -2.64
     ò
    -2.63
    phans
    -2.59
    warnai
    -2.59
    蔸
    -2.56
    POSITIVE LOGITS
    "
    3.09
    1
    2.97
    ↵↵
    2.77
    8
    2.67
    n
    2.67
    3
    2.56
    or
    2.53
    “
    2.53
    6
    2.52
    7
    2.48
    Activations Density 0.279%

    No Known Activations