© 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. 101519
    Prev
    Next
    INDEX
    Explanations

    conjunctions like "but" or "and"

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

    The neuron selectively fires on sentence-initial coordinating conjunctions (e.g. And, But).

    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
     both
    -1.66
     only
    -1.63
     ONLY
    -1.58
     
    -1.53
     mainly
    -1.50
     always
    -1.49
     being
    -1.45
    However
    -1.44
    というのも
    -1.40
     what
    -1.39
    POSITIVE LOGITS
    </i>
    1.61
    fillment
    1.59
    alia
    1.58
    </strong>
    1.52
    without
    1.52
     prachtige
    1.51
    yeah
    1.51
    aries
    1.49
    atique
    1.49
    ordered
    1.48
    Activations Density 0.016%

    No Known Activations