© 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. 75501
    Prev
    Next
    INDEX
    Explanations

    continuing actions and states

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

    The neuron activates on occurrences of the progressive verb “continuing.”

    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
     nahil
    -2.38
    寕
    -2.22
    eabouts
    -2.16
    鹛
    -2.09
     integri
    -2.09
    ’).
    -2.06
    镦
    -2.06
    塒
    -2.06
     riu
    -2.03
     lefs
    -2.00
    POSITIVE LOGITS
    9
    3.42
    "
    3.03
    ization
    2.80
    4
    2.66
    2
    2.56
    3
    2.55
    8
    2.52
    7
    2.39
    5
    2.30
    V
    2.25
    Activations Density 0.001%

    No Known Activations