© 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. 80725
    Prev
    Next
    INDEX
    Explanations

    tube design

    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
     only
    -1.61
     will
    -1.57
     one
    -1.49
     apenas
    -1.34
     deschis
    -1.28
     just
    -1.23
    怎么样
    -1.20
     not
    -1.19
     basado
    -1.17
    +}$
    -1.16
    POSITIVE LOGITS
     (
    1.52
    \_
    1.37
     菇
    1.28
    Including
    1.27
    utched
    1.25
     These
    1.23
     Также
    1.20
    have
    1.20
     Hinsicht
    1.20
     Ã
    1.20
    Activations Density 0.109%

    No Known Activations