© 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. 53947
    Prev
    Next
    INDEX
    Explanations

    partnerships and joint initiatives

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

    The neuron fires on formal business‐press phrasing announcing corporate partnerships or sponsorship deals.

    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
     constaté
    -0.98
     appris
    -0.83
    breviations
    -0.82
    endlich
    -0.81
    bierz
    -0.80
     Kombin
    -0.79
     conversa
    -0.79
    awaited
    -0.79
    Paw
    -0.78
     Lamont
    -0.78
    POSITIVE LOGITS
     services
    1.16
     its
    1.16
     support
    1.02
     recette
    0.96
     assistance
    0.96
    énération
    0.95
     help
    0.95
     monetary
    0.95
    archical
    0.94
     créations
    0.94
    Activations Density 0.046%

    No Known Activations