© 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. 69026
    Prev
    Next
    INDEX
    Explanations

    is or are followed by

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

    The neuron fires on copular or passive‐voice constructions, highlighting the noun and its complement around forms of “to be” (is/are).

    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
    Према
    -1.11
     thou
    -0.97
     with
    -0.94
    ⊐
    -0.89
     crustace
    -0.89
     takut
    -0.86
    ieważ
    -0.85
    чнее
    -0.85
    ∑
    -0.84
    these
    -0.83
    POSITIVE LOGITS
     necessary
    1.19
     another
    1.08
     וה
    1.05
     aspect
    1.02
     needed
    1.00
     obvious
    0.99
     part
    0.99
    पा
    0.99
     important
    0.97
     обеспе
    0.96
    Activations Density 0.101%

    No Known Activations