© 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. 10-GEMMASCOPE-RES-131K
    4. 57456
    Prev
    Next
    INDEX
    Explanations

    everything is

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

    The neuron is detecting instances of the copular verb “to be” (e.g. is, be, will be).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    anzug
    -1.47
    ländischen
    -1.35
     grotte
    -1.32
     új
    -1.30
     of
    -1.30
     uly
    -1.26
    läufig
    -1.26
     BorderRadius
    -1.23
     når
    -1.23
    鵞
    -1.22
    POSITIVE LOGITS
     everything
    1.80
    Everything
    1.70
     about
    1.69
     allerede
    1.62
     bereits
    1.52
     Everything
    1.41
    Things
    1.38
     actually
    1.35
     things
    1.32
     collaborated
    1.32
    Activations Density 0.045%

    No Known Activations