© 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. 22-GEMMASCOPE-RES-131K
    4. 54036
    Prev
    Next
    INDEX
    Explanations

    past participles in passive voice

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

    The neuron detects past-tense or past-participle verb forms (e.g. “called,” “removed,” “selected,” “engaged,” “identified,” “added,” “controlled,” “sung,” “fetched”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     senin
    -1.77
    あぁ
    -1.73
     organisme
    -1.72
    明日は
    -1.66
    えっ
    -1.63
     komik
    -1.60
     diki
    -1.59
    すっ
    -1.52
    ほら
    -1.52
    ごめん
    -1.48
    POSITIVE LOGITS
     from
    1.63
     be
    1.59
     with
    1.47
     regarding
    1.40
    ,
    1.38
     as
    1.30
     in
    1.27
    <td>
    1.26
     of
    1.23
     through
    1.20
    Activations Density 0.114%

    No Known Activations