© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26955
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     its
    -1.72
     their
    -1.29
    verre
    -1.06
    畾
    -1.06
     raccont
    -1.05
    ﻒ
    -1.04
    ahme
    -1.03
     only
    -1.02
    lampe
    -1.02
    нение
    -1.02
    POSITIVE LOGITS
     that
    1.41
    instead
    1.20
    excellents
    1.19
    Instead
    1.16
    でしたね
    1.14
    𝙪
    1.08
     względem
    1.08
     داشت
    1.06
     MATTERS
    1.05
    mişti
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.