© 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. 42180
    Prev
    Next
    INDEX
    Explanations

    ongoing actions

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

    The neuron activates on adverbs (especially “constantly”) and other words that signal ongoing or repeated actions.

    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
    皷
    -2.70
    "> 
    -2.45
     But
    -2.30
    locene
    -2.23
     ekster
    -2.20
    -2.19
    魉
    -2.17
    可能会
    -2.16
     blossom
    -2.16
    琚
    -2.14
    POSITIVE LOGITS
     був
    2.63
    there
    2.63
     =
    2.50
    其妙
    2.36
    new
    2.34
     был
    2.31
     gives
    2.19
    ]
    2.19
    ']
    2.17
    تیجه
    2.16
    Activations Density 0.006%
    No Known Activations