© 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. 123773
    Prev
    Next
    INDEX
    Explanations

    script tags

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

    whitespace and newlines in HTML code, particularly after closing script tags.

    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
     to
    -2.55
     either
    -1.69
     for
    -1.66
    着自己的
    -1.56
     then
    -1.53
     or
    -1.52
     "
    -1.48
     deteriorating
    -1.45
     noting
    -1.43
     wiederholt
    -1.43
    POSITIVE LOGITS
    ↵↵
    1.61
     Parlament
    1.51
    */
    
    1.48
    المصادر
    1.48
     
    1.45
     burbu
    1.45
     fumée
    1.44
    </h3>
    1.44
     ibang
    1.41
    kách
    1.38
    Activations Density 0.028%

    No Known Activations