© 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. 34-GEMMASCOPE-RES-131K
    4. 66267
    Prev
    Next
    INDEX
    Explanations

    content creation and consumption

    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_34/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
    enosti
    -0.78
    iseerd
    -0.78
    tragung
    -0.75
    ândia
    -0.75
     enkele
    -0.75
    Interment
    -0.75
     تت
    -0.73
    mRecyclerView
    -0.72
    FundMe
    -0.72
     egyes
    -0.71
    POSITIVE LOGITS
     content
    6.19
    content
    4.25
    Content
    3.72
    CONTENT
    3.52
     Content
    3.39
    内容
    3.34
     contents
    3.28
     contenido
    3.25
     CONTENT
    3.09
     contenu
    2.94
    Activations Density 0.123%

    No Known Activations