© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    books and reading

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

    The neuron responds to occurrences of “book” (and book-related forms like “books” or “bookish”).

    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
    Glossary
    -0.94
     GoPro
    -0.86
    webcam
    -0.84
    hörigen
    -0.82
    vimeo
    -0.82
     paintball
    -0.81
    殓
    -0.80
     Vimeo
    -0.78
     NEWSLETTER
    -0.78
    MPEG
    -0.78
    POSITIVE LOGITS
     library
    2.97
     literary
    2.84
     reading
    2.84
     libraries
    2.69
     books
    2.63
     Library
    2.58
     book
    2.56
     librarian
    2.42
    library
    2.42
     Libraries
    2.39
    Activations Density 0.139%

    No Known Activations