© 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. 104409
    Prev
    Next
    INDEX
    Explanations

    seeking clarification or information

    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
    Their
    -1.37
     lorsqu
    -1.26
     pokud
    -1.16
     wanneer
    -1.16
     keď
    -1.14
     Quando
    -1.14
     cuando
    -1.11
     jejich
    -1.10
    และ
    -1.09
     gdy
    -1.09
    POSITIVE LOGITS
     or
    2.77
     your
    2.27
     about
    1.59
     yourself
    1.48
     или
    1.44
     out
    1.29
    或
    1.19
     of
    1.16
     feel
    1.16
     this
    1.14
    Activations Density 0.022%

    No Known Activations