© 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. 34-GEMMASCOPE-RES-131K
    7. 66427
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs or main verbs

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

    The neuron fires on the first content token in each text snippet (i.e. it marks the start of each document segment).

    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
    ——”
    -1.96
    鲧
    -1.92
     corriger
    -1.91
    weren
    -1.88
    banez
    -1.87
     incrí
    -1.84
     italie
    -1.84
     délais
    -1.84
     montrer
    -1.83
     بودند
    -1.83
    POSITIVE LOGITS
     has
    3.59
     is
    3.56
     was
    3.33
     had
    2.77
     and
    2.77
     which
    2.75
     would
    2.72
     will
    2.70
     could
    2.44
     can
    2.38
    Activations Density 0.152%

    No Known Activations