© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69942
    Prev
    Next
    INDEX
    Explanations

    number followed by thirds or hundred or dimensional

    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_10/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
     what
    -1.90
    🢒
    -1.77
     how
    -1.74
     only
    -1.72
     making
    -1.60
     does
    -1.59
     use
    -1.59
     to
    -1.59
     while
    -1.55
     give
    -1.53
    POSITIVE LOGITS
     beter
    1.60
    )
    1.54
     bricola
    1.52
    檩
    1.50
    骉
    1.49
     injust
    1.48
    惬
    1.48
     faciliter
    1.48
     Dinas
    1.48
     Promotes
    1.48
    Activations Density 0.107%

    No Known Activations