© 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. 93099
    Prev
    Next
    INDEX
    Explanations

    is/are/was followed by adjectives

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

    The neuron activates on copular “to be” verbs (is/are/was) when they link subjects to descriptive complements.

    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
     this
    -1.42
    ceptable
    -1.41
    ícias
    -1.36
     cantora
    -1.25
    의
    -1.20
     then
    -1.19
    licante
    -1.18
    ryl
    -1.17
     return
    -1.16
     process
    -1.14
    POSITIVE LOGITS
     great
    1.30
     النبات
    1.29
     superbes
    1.26
     very
    1.23
    Eks
    1.22
     icône
    1.22
     musées
    1.20
     творо
    1.20
    อะไร
    1.19
    ,''
    1.17
    Activations Density 0.028%

    No Known Activations