© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9762
    Prev
    Next
    INDEX
    Explanations

    state of being or condition

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

    The neuron fires on occurrences of simple auxiliary or copular verbs—especially “is,” “does,” and “must”—in sentences.

    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
     они
    -1.69
     Mereka
    -1.55
    他們
    -1.55
     mereka
    -1.52
    
    -1.52
     levantó
    -1.48
     burada
    -1.47
     erfolgre
    -1.45
    錞
    -1.45
    Our
    -1.44
    POSITIVE LOGITS
    gées
    1.41
     then
    1.39
     are
    1.34
    /**
    1.32
    первых
    1.30
    Notre
    1.24
    ällig
    1.22
    瞻
    1.22
    \
    1.20
     وزیر
    1.19
    Activations Density 0.129%

    No Known Activations