© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    years and ordinals

    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
     is
    -2.05
     it
    -1.69
     to
    -1.59
     that
    -1.36
     then
    -1.31
     others
    -1.30
    还不错
    -1.26
     things
    -1.25
    されていて
    -1.24
     zucchero
    -1.21
    POSITIVE LOGITS
     of
    2.16
     on
    1.73
     nélk
    1.38
    ocimiento
    1.34
    罴
    1.28
     พ่อ
    1.27
     tomto
    1.26
     dessutom
    1.25
    InputBorder
    1.23
    Ⅳ
    1.21
    Activations Density 0.061%

    No Known Activations