© 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. 22-GEMMASCOPE-RES-131K
    7. 68243
    Prev
    Next
    INDEX
    Explanations

    be/been followed by past participle

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

    The neuron detects auxiliary “be” verbs—especially “been” and other forms of “be” 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_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
     kari
    -1.38
    ₨
    -1.34
    我们
    -1.18
    幸いです
    -1.16
     konkre
    -1.13
    衬衫
    -1.12
     hablaba
    -1.09
     verra
    -1.09
    Aktu
    -1.08
    hoea
    -1.05
    POSITIVE LOGITS
     there
    1.38
     available
    1.32
     that
    1.23
     those
    1.20
     eenvou
    1.09
     μεγά
    1.09
     thofe
    1.09
     this
    1.07
     occur
    1.05
     indruk
    1.02
    Activations Density 0.073%

    No Known Activations