© 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. 3663
    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
    LARATION
    -1.59
    vaných
    -1.52
    ,
    -1.47
     vuotta
    -1.42
    k
    -1.40
     -(
    -1.37
    ኧ
    -1.37
     indef
    -1.37
     '(
    -1.35
    orsing
    -1.35
    POSITIVE LOGITS
    2.50
    .
    2.38
     sharp
    1.58
    آباد
    1.55
     “
    1.50
    ,

    1.47
     flesta
    1.43
     zwięks
    1.42
     our
    1.41
    目
    1.40
    Activations Density 0.000%
    No Known Activations
    This feature has no known activations.