© 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. 39714
    Prev
    Next
    INDEX
    Explanations

    memorial service, live coverage, match play

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

    This neuron detects event-related keywords, such as terms denoting memorial services (“memorial”) or live broadcasts (“Live”).

    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
     mêmes
    -1.24
     což
    -1.19
     peuvent
    -1.19
    癭
    -1.16
     meubles
    -1.16
     même
    -1.16
     komplette
    -1.16
     ainsi
    -1.15
    
    -1.13
     déchets
    -1.12
    POSITIVE LOGITS
     and
    1.37
     any
    1.33
     at
    1.33
     heightened
    1.32
     Extremely
    1.23
     widespread
    1.22
     nestled
    1.22
     after
    1.22
     in
    1.20
     west
    1.20
    Activations Density 0.000%

    No Known Activations