© 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. 102913
    Prev
    Next
    INDEX
    Explanations

    ring

    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
    5
    -2.56
    6
    -2.53
     \
    -2.20
    4
    -2.20
    u
    -2.20
    {
    -2.17
    s
    -2.14
     you
    -2.14
    x
    -2.14
    0
    -2.09
    POSITIVE LOGITS
     confirmado
    2.08
     évek
    2.03
    鄖
    2.03
    鴣
    2.03
    рами
    2.02
     registrada
    1.99
     escribiendo
    1.99
    数を
    1.99
     inglesa
    1.98
     Questo
    1.95
    Activations Density 0.008%

    No Known Activations