© 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. 101920
    Prev
    Next
    INDEX
    Explanations

    great + positive descriptor

    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
    7
    -1.58
    9
    -1.53
     炖
    -1.28
     zamiast
    -1.27
     comprennent
    -1.26
     montrent
    -1.25
     donnent
    -1.24
    鲼
    -1.23
     assurent
    -1.23
     verbess
    -1.23
    POSITIVE LOGITS
     some
    1.50
    цыі
    1.46
    ppuden
    1.44
     Weltkrieg
    1.30
     mö
    1.29
     through
    1.26
    odyne
    1.25
    TintMode
    1.23
     kön
    1.23
    两者
    1.22
    Activations Density 0.024%

    No Known Activations