© 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. 10-GEMMASCOPE-RES-131K
    4. 11632
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

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

    The neuron detects past-participle verbs (especially regular verbs ending in “-ed”) often used in passive 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
     cheio
    -1.43
     échanti
    -1.38
     procé
    -1.36
     spektak
    -1.32
     feita
    -1.31
     cheveux
    -1.31
     gomma
    -1.28
     
    -1.27
     aime
    -1.27
     gier
    -1.27
    POSITIVE LOGITS
     by
    1.98
     There
    1.92
     in
    1.80
     with
    1.68
     for
    1.67
     as
    1.60
    There
    1.57
    icona
    1.51
     a
    1.50
     out
    1.48
    Activations Density 0.172%

    No Known Activations