© 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. 73569
    Prev
    Next
    INDEX
    Explanations

    sql `select` and `join` statements

    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
     With
    -1.51
    écuter
    -1.31
     It
    -1.31
     de
    -1.27
     And
    -1.27
    付けて
    -1.24
    phylla
    -1.21
     Impf
    -1.21
     As
    -1.20
     île
    -1.16
    POSITIVE LOGITS
    jelaskan
    1.45
     چیزی
    1.45
     選手
    1.42
    そんな
    1.41
     everything
    1.38
     vienas
    1.38
     díky
    1.27
     viena
    1.27
     wszystkie
    1.26
     būt
    1.26
    Activations Density 0.035%

    No Known Activations