© 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. 93834
    Prev
    Next
    INDEX
    Explanations

    discussing book titles, authors, and publication

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    壁纸
    -0.98
     Booklet
    -0.96
     contempl
    -0.95
    的东西
    -0.91
    тування
    -0.91
     confr
    -0.91
     Oedipus
    -0.90
     obicei
    -0.90
    мені
    -0.90
    툰
    -0.88
    POSITIVE LOGITS
     about
    1.55
    helves
    1.45
     by
    1.30
     series
    1.20
    keeper
    1.17
    length
    1.16
     jacket
    1.16
     publishers
    1.16
     written
    1.14
     published
    1.14
    Activations Density 0.023%

    No Known Activations