© 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. 41635
    Prev
    Next
    INDEX
    Explanations

    require, useState, props

    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
     dlouho
    -1.51
     liknande
    -1.37
    兩
    -1.34
     hodně
    -1.33
    你和
    -1.26
    Astronom
    -1.24
    aguars
    -1.23
     rů
    -1.23
    宕
    -1.23
     přek
    -1.21
    POSITIVE LOGITS
     they
    1.95
     already
    1.45
     Connectez
    1.42
     even
    1.38
     nouveautés
    1.30
     available
    1.29
     there
    1.27
     даже
    1.27
     mundos
    1.27
     Ouvrez
    1.24
    Activations Density 0.005%

    No Known Activations