© 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. 79620
    Prev
    Next
    INDEX
    Explanations

    state description after 'to be'

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

    The neuron fires on common forms of the verb “to be” (e.g. “is,” “are,” “been”).

    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
     dôle
    -1.45
     important
    -1.20
     verschillen
    -1.19
    了一些
    -1.18
     môžete
    -1.18
     aiutare
    -1.16
    ętr
    -1.14
    <bos>
    -1.12
     tärke
    -1.11
     pracov
    -1.09
    POSITIVE LOGITS
     with
    1.46
     دارای
    1.30
     able
    1.20
     tricot
    1.12
    有
    1.08
     equipped
    1.02
     Wifi
    1.01
     LISTING
    1.00
     bygg
    1.00
    มี
    1.00
    Activations Density 0.177%

    No Known Activations