© 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. 10-GEMMASCOPE-RES-131K
    7. 59827
    Prev
    Next
    INDEX
    Explanations

    award names and entities

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

    The neuron fires on numeric tokens—especially numbers denoting awards, honors, or other formal distinctions.

    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
     litri
    -1.57
     maniere
    -1.47
     acessar
    -1.47
     incredi
    -1.45
     すぐ
    -1.38
     alcuni
    -1.37
     atingir
    -1.37
     alimentare
    -1.36
     alcune
    -1.35
     cantit
    -1.35
    POSITIVE LOGITS
     of
    2.63
     by
    2.38
     all
    2.11
     both
    2.09
     even
    2.09
     after
    2.02
     not
    1.96
     for
    1.88
     in
    1.87
     high
    1.78
    Activations Density 0.131%

    No Known Activations