© 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. 31790
    Prev
    Next
    INDEX
    Explanations

    Shakespeare and his plays

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

    The neuron strongly activates on mentions of Shakespeare or his works.

    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
    ﻋ
    -0.80
    AER
    -0.79
     Sahara
    -0.79
     Raid
    -0.78
    gitlab
    -0.78
     Turin
    -0.76
     daß
    -0.75
     Ame
    -0.74
     Bering
    -0.74
    akhstan
    -0.73
    POSITIVE LOGITS
     Shakespeare
    3.20
    Shakespeare
    3.05
     Macbeth
    2.31
    Hamlet
    2.30
     Hamlet
    2.22
    kespeare
    1.91
     Shakes
    1.88
     Othello
    1.82
     Romeo
    1.68
    Romeo
    1.62
    Activations Density 0.031%

    No Known Activations