© 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. 105429
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    The neuron strongly activates on common coordinating conjunctions (e.g. “and,” “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
    ."
    -1.93
     they
    -1.89
     because
    -1.80
     when
    -1.72
     cuando
    -1.56
     who
    -1.56
     which
    -1.53
    .
    -1.47
     EditText
    -1.46
    Forums
    -1.45
    POSITIVE LOGITS
     are
    2.67
    ꟷ
    1.48
    lichung
    1.44
    
    1.39
     Nhưng
    1.37
     Tropfen
    1.34
    年来
    1.34
    也会
    1.33
     —
    1.31
    探讨
    1.31
    Activations Density 0.322%

    No Known Activations