© 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. 129284
    Prev
    Next
    INDEX
    Explanations

    code identifiers and syntax

    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
     negó
    -1.66
    {
    -1.52
     aumentado
    -1.52
     efectiva
    -1.50
     a
    -1.48
     need
    -1.46
     needs
    -1.45
     servido
    -1.42
     valioso
    -1.41
     applies
    -1.41
    POSITIVE LOGITS
     pamoja
    1.66
     hän
    1.62
     sué
    1.62
    0
    1.62
     espagnol
    1.55
    6
    1.43
    4
    1.38
    炱
    1.38
     turquoise
    1.38
     africain
    1.37
    Activations Density 0.001%

    No Known Activations