© 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. 8298
    Prev
    Next
    INDEX
    Explanations

    novel

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

    The neuron fires strongly on the word “novel,” flagging instances where a text introduces something as new or novel.

    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
    <bos>
    -2.50
    歃
    -2.36
     maravilh
    -2.05
    扨
    -2.00
    嫱
    -1.98
     occupé
    -1.95
     wichtigsten
    -1.94
     Reſ
    -1.91
     perfeita
    -1.90
    鲵
    -1.87
    POSITIVE LOGITS
    e
    2.22
     untuk
    1.95
    m
    1.92
    .
    1.90
     –
    1.88
     влади
    1.83
     but
    1.80
    changers
    1.77
    汌
    1.76
     Novels
    1.74
    Activations Density 0.014%

    No Known Activations