© 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. 43706
    Prev
    Next
    INDEX
    Explanations

    web browser, menu, license

    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
     NOT
    -1.41
     QtWidgets
    -1.34
    ଃ
    -1.31
    enschutz
    -1.30
     самых
    -1.30
     året
    -1.29
     kompeti
    -1.27
     tertawa
    -1.26
    ERS
    -1.25
     vier
    -1.21
    POSITIVE LOGITS
     previos
    1.47
     here
    1.41
    وافق
    1.40
     vollen
    1.31
    过来了
    1.25
     دخترانه
    1.23
     ursprünglichen
    1.23
    nexpected
    1.23
     einzigartige
    1.23
     verbess
    1.22
    Activations Density 0.143%

    No Known Activations