© 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. 79959
    Prev
    Next
    INDEX
    Explanations

    website links and 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
     sidang
    -1.05
    Alguns
    -0.91
    _))
    -0.90
     beiden
    -0.85
    шением
    -0.82
    )}]{
    -0.82
    ]));
    -0.82
     cantidades
    -0.81
     Versand
    -0.81
    มัน
    -0.80
    POSITIVE LOGITS
     website
    1.68
     FAQs
    1.59
     about
    1.46
     webpage
    1.41
     page
    1.23
     homepage
    1.21
    ViewBag
    1.14
     wiki
    1.11
     FAQ
    1.11
    about
    1.10
    Activations Density 0.034%

    No Known Activations