© 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. 58828
    Prev
    Next
    INDEX
    Explanations

    length and width in inches

    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
     which
    -1.20
     by
    -1.02
     as
    -0.96
     at
    -0.93
     before
    -0.86
     dni
    -0.85
     solely
    -0.84
    Saturday
    -0.84
     perhaps
    -0.82
     Saturday
    -0.82
    POSITIVE LOGITS
     inches
    1.38
     inch
    1.07
     ≈
    0.95
     pulgadas
    0.92
    inches
    0.92
     width
    0.91
    inch
    0.90
     jūs
    0.88
    ི
    0.87
    sigkeit
    0.86
    Activations Density 0.004%

    No Known Activations