© 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. 68486
    Prev
    Next
    INDEX
    Explanations

    web page routing

    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
    '}';
    -1.02
     rövid
    -0.99
     from
    -0.96
    cardia
    -0.92
    </sup>
    -0.92
    chaikovsky
    -0.88
     ľudí
    -0.87
    }}^{\
    -0.86
    质量
    -0.85
    】
    -0.83
    POSITIVE LOGITS
     page
    1.18
     website
    1.15
    cestors
    1.05
     PRINCE
    1.02
     AJAX
    1.02
     HttpServlet
    1.02
     ajax
    1.01
     calendrier
    1.00
     MEANS
    1.00
     pages
    0.98
    Activations Density 0.029%

    No Known Activations