© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74449
    Prev
    Next
    INDEX
    Explanations

    time periods and superlatives

    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_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
    joyed
    -1.95
     rajut
    -1.89
    崀
    -1.87
    ܊
    -1.82
     plastiques
    -1.82
     kapak
    -1.80
     kalender
    -1.80
     velg
    -1.77
    theres
    -1.73
    蚡
    -1.73
    POSITIVE LOGITS
     in
    3.22
     on
    2.47
     at
    2.34
     for
    2.16
     last
    2.14
     prevent
    1.90
     by
    1.90
     then
    1.86
     provide
    1.86
     of
    1.85
    Activations Density 0.018%

    No Known Activations