© 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. 22-GEMMASCOPE-RES-131K
    7. 66698
    Prev
    Next
    INDEX
    Explanations

    boolean `true` and `false` values

    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_22/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
     with
    -1.31
     There
    -1.19
     Even
    -1.06
     first
    -1.01
    తా
    -0.97
     there
    -0.96
     where
    -0.94
     well
    -0.93
     menina
    -0.92
    ﻷ
    -0.91
    POSITIVE LOGITS
     Ember
    1.06
    bleshooting
    0.93
    ómetro
    0.91
     geliefert
    0.90
    Ember
    0.88
     déta
    0.88
    edance
    0.87
     Cz
    0.85
     Violet
    0.84
     Scorpio
    0.84
    Activations Density 0.028%

    No Known Activations