© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    but, although, though

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

    The neuron fires on auxiliary and modal verbs (e.g. “can,” “is,” “be,” “don’t”) marking clauses that express ability, possibility, or stance.

    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
     MessageBoxIcon
    -1.55
    蝌
    -1.48
     quieran
    -1.45
    でも
    -1.41
    illou
    -1.40
    せっかく
    -1.34
    ſſes
    -1.33
    Bagaimana
    -1.33
     hogyan
    -1.33
     However
    -1.32
    POSITIVE LOGITS
     its
    2.28
     it
    1.73
     entstand
    1.60
     other
    1.56
     to
    1.48
     quente
    1.46
     they
    1.39
    :
    1.39
    那一
    1.34
    still
    1.34
    Activations Density 0.058%

    No Known Activations