© 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. 10-GEMMASCOPE-RES-131K
    7. 67246
    Prev
    Next
    INDEX
    Explanations

    quoted names and terms

    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
     可愛い
    -1.48
    Aktuelle
    -1.33
    我
    -1.30
    鄚
    -1.29
    праж
    -1.27
     членов
    -1.27
    Different
    -1.24
    Therefore
    -1.23
     variadas
    -1.23
     かわいい
    -1.21
    POSITIVE LOGITS
    都有
    1.28
     of
    1.24
    ",
    1.22
     Tư
    1.19
     том
    1.16
     sử
    1.16
    fortunes
    1.16
    IIIIIIII
    1.16
     usar
    1.15
     포함
    1.15
    Activations Density 0.012%

    No Known Activations