© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115982
    Prev
    Next
    INDEX
    Explanations

    sonnets and poems

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

    The neuron spotlights mentions of poetry—especially specific poetic forms, works, and famous poem titles.

    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
     Padilla
    -0.81
     SPECIFICATION
    -0.75
     WPA
    -0.74
    设计师
    -0.74
    iban
    -0.73
     accordion
    -0.71
    forgettable
    -0.71
     Zent
    -0.69
    abre
    -0.69
     emprend
    -0.69
    POSITIVE LOGITS
     Son
    1.19
     sonnet
    1.18
     Petr
    1.05
    Petr
    1.03
     Shakespeare
    0.89
    volta
    0.86
     SON
    0.85
    Son
    0.82
    ailing
    0.79
     son
    0.79
    Activations Density 0.018%

    No Known Activations