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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48053
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    to
    -3.00
    7
    -2.66
    3
    -2.61
    ку
    -2.55
     
    -2.52
    .
    -2.50
    2
    -2.48
    6
    -2.38
    4
    -2.28
    5
    -2.23
    POSITIVE LOGITS
    quelize
    2.63
     rezultat
    2.52
    骘
    2.11
     it
    2.11
     which
    2.08
    遄
    2.06
     without
    2.05
     with
    2.05
    熊猫
    2.03
     bytu
    1.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.