© 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. 22-GEMMASCOPE-RES-131K
    7. 130545
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_22/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
     it
    -1.19
     each
    -1.18
     only
    -1.17
     permet
    -1.16
    ΑΣ
    -1.13
     new
    -1.09
    prender
    -1.09
    ΡΟ
    -1.07
     either
    -1.06
    rebbe
    -1.06
    POSITIVE LOGITS
    暧
    1.25
    mice
    1.09
     his
    1.09
    licative
    1.08
     darbo
    1.08
     jūs
    1.07
     حيث
    1.06
     imóvel
    1.04
    别人的
    1.03
    ttä
    1.02
    Activations Density 0.041%

    No Known Activations