© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93498
    Prev
    Next
    INDEX
    Explanations

    date and author annotations

    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
     authors
    -1.28
     autori
    -1.23
    作者
    -1.17
     Authors
    -1.13
     seksi
    -1.07
    authors
    -1.05
    Authors
    -1.04
     Автор
    -1.04
     ister
    -1.02
     AUTHORS
    -1.02
    POSITIVE LOGITS
     date
    2.23
     Date
    1.76
    date
    1.61
     dates
    1.61
     since
    1.53
     time
    1.48
     email
    1.38
     on
    1.29
    Date
    1.23
     dated
    1.18
    Activations Density 0.035%

    No Known Activations