© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112046
    Prev
    Next
    INDEX
    Explanations

    web links and code structures

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

    URLs or domain names in code, particularly those referencing external JavaScript libraries and CDN resources.

    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
     still
    -1.79
    ’
    -1.53
     "
    -1.50
     STILL
    -1.49
     “
    -1.45
     has
    -1.43
     isn
    -1.38
     hasn
    -1.33
     $
    -1.30
     könnten
    -1.27
    POSITIVE LOGITS
    lète
    1.43
     lära
    1.35
     voegen
    1.34
    jedno
    1.34
     those
    1.33
     zobac
    1.32
    jections
    1.31
    뚜
    1.31
    ıda
    1.30
    lihatan
    1.30
    Activations Density 0.017%

    No Known Activations