© 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. 98525
    Prev
    Next
    INDEX
    Explanations

    informal or archaic vocatives and interjections

    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
     its
    -1.22
     everybody
    -1.09
     everything
    -1.05
    וּ
    -1.04
     allmäh
    -1.04
     يمكن
    -1.03
     llenar
    -1.01
     maybe
    -1.01
    blooded
    -0.99
    busters
    -0.98
    POSITIVE LOGITS
    missie
    1.22
    lioni
    1.16
     که
    1.16
     весьма
    1.13
    It
    1.13
     ー
    1.12
     berkata
    1.12
    getLatitude
    1.11
    льного
    1.11
    尽管
    1.10
    Activations Density 0.059%

    No Known Activations