© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64462
    Prev
    Next
    INDEX
    Explanations

    Wrestler departures and goodbyes

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

    The neuron fires on names, titles, and other capitalized wrestling-related entities (e.g. wrestler names, event titles, and WWE program or game names).

    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
    stealth
    -0.78
    sourceType
    -0.73
     Compañ
    -0.73
    Referanser
    -0.73
    父の
    -0.72
    Regi
    -0.71
    產生
    -0.71
     Contamination
    -0.71
    CONF
    -0.70
    CompanyId
    -0.70
    POSITIVE LOGITS
    Tables
    1.12
     Tables
    1.02
     tables
    0.95
    steel
    0.87
     TABLES
    0.87
     Fuj
    0.81
    tables
    0.79
     TLC
    0.78
    Table
    0.77
     table
    0.76
    Activations Density 0.009%

    No Known Activations