© 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. 10-GEMMASCOPE-RES-131K
    7. 69316
    Prev
    Next
    INDEX
    Explanations

    book of X titles

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

    The neuron detects occurrences of the phrase “Book of …” marking titles introduced by “Book of” followed by a name.

    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
    黾
    -1.85
    </sup>
    -1.85
    蚰
    -1.73
    鹩
    -1.70
    romeda
    -1.70
    '\\
    -1.68
    ↵↵
    -1.67
    isierung
    -1.65
     schnee
    -1.64
    '...
    -1.63
    POSITIVE LOGITS
    ⑉
    2.38
    ៚
    2.16
    ⇴
    1.96
     resembling
    1.93
    鴣
    1.86
     divertimento
    1.85
    CurtirCurtir
    1.82
     должна
    1.81
     Wartawan
    1.79
    淶
    1.79
    Activations Density 0.008%

    No Known Activations