© 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. 10-GEMMASCOPE-RES-131K
    7. 44723
    Prev
    Next
    INDEX
    Explanations

    rhyme and time

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

    The main thing this neuron does is detect mentions of rhyming or rhyme-based literary elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    for
    -2.39
     др
    -2.39
    }$.
    -2.39
    ”;
    -2.38
     '')
    -2.34
    ஂ
    -2.31
    de
    -2.28
    ꦢ
    -2.17
    orsese
    -2.17
    ]
    -2.16
    POSITIVE LOGITS
     chcete
    2.09
    ができます
    2.03
    𐬹
    2.02
    筇
    2.00
     contextos
    1.98
     máte
    1.97
     futile
    1.97
     couples
    1.94
    lässlich
    1.92
     escribiendo
    1.91
    Activations Density 0.002%

    No Known Activations