© 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. 34-GEMMASCOPE-RES-131K
    7. 93926
    Prev
    Next
    INDEX
    Explanations

    trees and specific types

    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_34/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
    aktur
    -0.93
    QMetaType
    -0.82
     compacted
    -0.80
    istiche
    -0.79
     prone
    -0.77
    Đi
    -0.77
    titur
    -0.76
     gamble
    -0.73
    aragus
    -0.73
    namic
    -0.72
    POSITIVE LOGITS
     trees
    1.55
     tree
    1.52
     Tree
    1.23
    trees
    1.16
    tree
    1.11
     Grove
    1.11
     TREES
    1.11
     Trees
    1.05
    Trees
    1.02
     grove
    1.00
    Activations Density 0.018%

    No Known Activations