© 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. 9795
    Prev
    Next
    INDEX
    Explanations

    verbs and adverbs followed by details

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

    The neuron selectively activates on past participle verbs (particularly those used in passive‐voice constructions).

    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
    糌
    -1.61
     любую
    -1.61
     quelque
    -1.59
     elegan
    -1.56
    EVERY
    -1.48
    댔
    -1.48
    襌
    -1.44
     любые
    -1.43
    preduce
    -1.43
     CREAT
    -1.43
    POSITIVE LOGITS
     from
    2.72
     this
    2.20
     to
    2.00
     as
    1.98
     through
    1.98
     various
    1.96
     with
    1.95
     that
    1.94
     on
    1.90
     new
    1.90
    Activations Density 0.121%

    No Known Activations