© 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. 92884
    Prev
    Next
    INDEX
    Explanations

    modern updates of classic styles

    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
    ּוֹ
    -1.21
     entrenar
    -1.18
     inmueble
    -1.16
    ֵּ
    -1.14
     vientos
    -1.11
     когато
    -1.10
     trabajan
    -1.08
     cuidar
    -1.06
    mejores
    -1.05
     sufren
    -1.05
    POSITIVE LOGITS
     modern
    1.78
     moderne
    1.48
    modern
    1.44
     new
    1.43
     современ
    1.34
     moderna
    1.30
    现代
    1.27
     nowoczes
    1.23
     contemporary
    1.20
     moderno
    1.16
    Activations Density 0.034%

    No Known Activations