© 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. 7839
    Prev
    Next
    INDEX
    Explanations

    visits

    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
    mathrm
    -1.52
    atized
    -1.31
     élégante
    -1.26
     muñeco
    -1.26
     colchón
    -1.23
     \
    -1.23
     niem
    -1.22
     zdjęcie
    -1.21
    lers
    -1.20
     mariée
    -1.20
    POSITIVE LOGITS
     used
    1.52
     here
    1.39
     if
    1.38
     would
    1.30
     have
    1.23
     it
    1.20
     will
    1.16
     our
    1.16
     There
    1.14
    身心
    1.13
    Activations Density 0.118%

    No Known Activations