© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82380
    Prev
    Next
    INDEX
    Explanations

    award ceremonies

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

    The neuron flags references to award events or sponsorships (mentions of “award,” “awards,” “sponsor,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     using
    -0.90
     approved
    -0.84
     non
    -0.83
     activities
    -0.82
     artificially
    -0.82
     more
    -0.81
    世紀
    -0.81
     аппетита
    -0.80
     meetings
    -0.79
     Ausblick
    -0.79
    POSITIVE LOGITS
     awards
    2.23
    Awards
    1.97
     Awards
    1.95
    awards
    1.71
     award
    1.71
     ceremony
    1.63
    Award
    1.59
     Award
    1.54
     церемо
    1.51
     judges
    1.49
    Activations Density 0.033%

    No Known Activations