© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    specific entities and actions

    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
    ınıza
    -1.50
     our
    -1.34
     réessayer
    -1.31
    んでいた
    -1.30
     обратно
    -1.30
    的看着
    -1.29
    ẕ
    -1.29
    地看着
    -1.25
    באנגלית
    -1.24
    ḏ
    -1.24
    POSITIVE LOGITS
    𓏸
    1.75
    𓂂
    1.67
     ideia
    1.55
    ﻹ
    1.51
    iramente
    1.48
     recibo
    1.48
    𝐳
    1.47
    🧫
    1.47
     obispo
    1.43
    ﻷ
    1.40
    Activations Density 0.075%

    No Known Activations