© 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. 59133
    Prev
    Next
    INDEX
    Explanations

    award show names

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

    The neuron fires on names of awards shows and music‐industry organizations (e.g. “Academy,” “Country,” “Music,” “ACM,” “Awards”).

    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
     сло
    -0.81
    り
    -0.78
     recommended
    -0.76
    .$
    -0.73
    Jeografia
    -0.71
    záll
    -0.70
    そう
    -0.69
    Team
    -0.68
     Schubert
    -0.68
    بند
    -0.68
    POSITIVE LOGITS
     awards
    2.61
     Awards
    2.23
    Awards
    1.90
     award
    1.87
     ceremony
    1.74
     Award
    1.67
    awards
    1.63
     AWARDS
    1.59
     ceremonies
    1.42
    Award
    1.42
    Activations Density 0.031%

    No Known Activations