© 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. 80754
    Prev
    Next
    INDEX
    Explanations

    width and size measurements

    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
     fortalec
    -0.99
    curité
    -0.95
    Çok
    -0.94
     UIApplication
    -0.91
    arraycopy
    -0.90
    QColor
    -0.90
    Açık
    -0.88
    engesch
    -0.86
    urgi
    -0.86
    Liefs
    -0.84
    POSITIVE LOGITS
     width
    2.84
     size
    2.66
     sizes
    2.33
     dimensions
    2.25
    width
    2.19
    size
    2.17
     Width
    2.17
     widths
    2.16
     Size
    2.11
     sizing
    2.05
    Activations Density 0.096%

    No Known Activations