© 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. 61229
    Prev
    Next
    INDEX
    Explanations

    singular quantification

    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
     gastronomía
    -2.02
     procéder
    -1.81
    詆
    -1.72
     artesanía
    -1.71
    -1.64
     pères
    -1.64
     capucha
    -1.64
               
    -1.62
     театр
    -1.61
    ﻻ
    -1.61
    POSITIVE LOGITS
     one
    2.28
     проє
    2.17
     any
    2.08
     with
    2.00
     hacían
    1.96
     дисци
    1.86
     at
    1.73
     to
    1.71
     ajang
    1.67
     every
    1.64
    Activations Density 0.172%

    No Known Activations