© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12245
    Prev
    Next
    INDEX
    Explanations

    localhost URLs

    np_acts-logits-general · gemini-2.5-flash-lite

    forward slashes in localhost URLs, particularly in development/testing contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    _
    -2.16
    1
    -1.98
    なども
    -1.98
    の方も
    -1.82
     also
    -1.79
     That
    -1.73
     последних
    -1.69
    Also
    -1.68
     segurando
    -1.66
    瓩
    -1.65
    POSITIVE LOGITS
    "+
    
    1.82
    '},
    
    1.82
    ждении
    1.73
     députés
    1.72
    "),
    
    1.68
    wendi
    1.66
    ☑️
    1.63
    嚀
    1.62
    #
    
    1.61
    %");
    1.61
    Activations Density 0.017%

    No Known Activations