© 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. 10-GEMMASCOPE-RES-131K
    7. 123504
    Prev
    Next
    INDEX
    Explanations

    css class names like wrapper

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

    the word "wrapper" in HTML/code class attributes.

    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
    -2.09
     or
    -2.03
     such
    -1.78
     piemē
    -1.70
     when
    -1.63
     Aussehen
    -1.54
     menggunakan
    -1.54
     Erinner
    -1.52
     ditambah
    -1.51
     since
    -1.49
    POSITIVE LOGITS
     savent
    1.59
    进入了
    1.56
     bascul
    1.51
     barres
    1.40
     marte
    1.40
     herbes
    1.40
     boutons
    1.39
     humeur
    1.36
     entré
    1.36
     eaux
    1.36
    Activations Density 0.016%

    No Known Activations