© 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. 34-GEMMASCOPE-RES-131K
    7. 86793
    Prev
    Next
    INDEX
    Explanations

    text content or fields

    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
    iastical
    -0.79
     изделия
    -0.75
    ilov
    -0.74
    nameLabel
    -0.73
     setName
    -0.71
    ürzen
    -0.70
    phanie
    -0.70
     requestCode
    -0.70
    τικής
    -0.69
    gae
    -0.69
    POSITIVE LOGITS
     content
    3.70
    内容
    2.86
    content
    2.84
     contents
    2.83
    內容
    2.47
     text
    2.44
     contenido
    2.27
     내용
    2.27
     body
    2.20
    Content
    2.19
    Activations Density 0.073%

    No Known Activations