© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31090
    Prev
    Next
    INDEX
    Explanations

    Shakespeare and works

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     geo
    -0.82
    lassified
    -0.73
    èbre
    -0.72
     бел
    -0.71
    vals
    -0.71
    ECA
    -0.71
     поверх
    -0.70
    ZN
    -0.69
    nání
    -0.68
     ai
    -0.68
    POSITIVE LOGITS
     Shakespeare
    1.90
    Shakespeare
    1.74
     Stratford
    1.58
    Strat
    1.24
     Warwickshire
    1.18
     Elizabethan
    1.09
     Shakspeare
    1.08
     bard
    1.07
    Hamlet
    1.07
    Romeo
    1.02
    Activations Density 0.019%

    No Known Activations