© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7302
    Prev
    Next
    INDEX
    Explanations

    technical specification parameters

    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
    Its
    -1.38
     doesnt
    -1.38
    Both
    -1.38
     guapos
    -1.32
    ที่จะ
    -1.30
     när
    -1.26
     your
    -1.21
    4
    -1.20
    悲伤
    -1.20
    All
    -1.20
    POSITIVE LOGITS
     are
    1.67
     rapidamente
    1.41
     then
    1.41
    麁
    1.37
     aumentando
    1.31
     ナチュラル
    1.30
     kind
    1.30
     protože
    1.24
     permanecer
    1.22
     árvores
    1.22
    Activations Density 0.000%

    No Known Activations