© 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. 65748
    Prev
    Next
    INDEX
    Explanations

    pixel and dimension values

    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
     width
    -2.02
    WIDTH
    -1.85
     Width
    -1.79
    width
    -1.73
     WIDTH
    -1.69
    Width
    -1.65
    HEIGHT
    -1.53
     widths
    -1.53
     height
    -1.44
    宽度
    -1.41
    POSITIVE LOGITS
     Rag
    0.82
    ImageBackground
    0.80
    artiges
    0.78
     Sula
    0.73
    movq
    0.73
    ρια
    0.72
    Kura
    0.71
    Forsch
    0.71
     it
    0.70
    mia
    0.69
    Activations Density 0.043%

    No Known Activations