© 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. 13227
    Prev
    Next
    INDEX
    Explanations

    organizational names

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

    The neuron fires on multi‐word corporate or institutional names—that is, organization name entities.

    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
     their
    -2.58
     that
    -2.38
     from
    -1.98
     joyas
    -1.92
     this
    -1.90
     at
    -1.70
     quite
    -1.65
     after
    -1.63
     undeniably
    -1.62
     probably
    -1.61
    POSITIVE LOGITS
     모든
    1.66
     コットン
    1.63
     flamboyant
    1.55
     ayur
    1.55
     Dinas
    1.55
     xan
    1.48
     unn
    1.44
     disting
    1.43
     stic
    1.41
     ストレッチ
    1.40
    Activations Density 0.031%

    No Known Activations