© 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. 84632
    Prev
    Next
    INDEX
    Explanations

    image, info, link, caption

    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
     pictures
    -2.02
    图片
    -1.93
    imageUrl
    -1.84
     picture
    -1.83
     imageUrl
    -1.81
     photographs
    -1.78
     photograph
    -1.75
     imagery
    -1.73
     photographic
    -1.70
    picture
    -1.70
    POSITIVE LOGITS
     audio
    0.93
     description
    0.87
     text
    0.87
     alt
    0.82
     background
    0.82
     backgrounds
    0.79
    背后的
    0.79
     caption
    0.78
     sounds
    0.78
     captions
    0.77
    Activations Density 0.055%

    No Known Activations