© 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. 22-GEMMASCOPE-RES-131K
    7. 36587
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

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

    The neuron primarily detects the conjunction “and.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     både
    -2.09
     salonu
    -1.99
    辚
    -1.91
    archiwizowane
    -1.87
    /"
    -1.86
    vantaged
    -1.82
     televiz
    -1.80
    ПРИ
    -1.78
     bakteri
    -1.75
    퓰
    -1.75
    POSITIVE LOGITS
     then
    3.14
    A
    2.33
     a
    2.27
     consequently
    2.16
     so
    2.08
        
    2.05
    As
    2.00
     others
    1.93
     subsequently
    1.93
     before
    1.92
    Activations Density 0.030%

    No Known Activations