© 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. 19857
    Prev
    Next
    INDEX
    Explanations

    And followed by connector

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

    The neuron flags occurrences of the conjunction “And,” especially when it appears as a sentence-initial or standalone “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_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
     also
    -2.16
     Also
    -1.80
     
    -1.77
     bzw
    -1.69
     In
    -1.66
     arī
    -1.62
     Y
    -1.61
     &
    -1.60
     también
    -1.60
     of
    -1.59
    POSITIVE LOGITS
    躥
    2.00
    EdgeInsets
    1.95
    ⟿
    1.84
     fluide
    1.84
    鱻
    1.83
    踯
    1.80
     isra
    1.79
    __('
    1.79
    %"),
    1.77
     lisse
    1.77
    Activations Density 0.036%

    No Known Activations