© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48060
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" + participle

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

    The neuron activates on occurrences of the verb “to be” in its various forms (is, are, was, were).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     캐
    -0.82
     autofocus
    -0.81
    Ouest
    -0.77
    attoos
    -0.77
     rename
    -0.76
    eigen
    -0.76
    排名
    -0.75
     classified
    -0.75
    Classified
    -0.75
     regroup
    -0.74
    POSITIVE LOGITS
     notified
    1.95
     alerted
    1.83
     contacted
    1.80
     consulted
    1.34
     invoked
    1.27
     aware
    1.20
     called
    1.05
     unaware
    1.01
     informed
    0.99
     present
    0.99
    Activations Density 0.042%

    No Known Activations