© 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. 130867
    Prev
    Next
    INDEX
    Explanations

    gasping, gulp, cusp, chug

    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
    躥
    -2.56
    鉝
    -2.36
    
    -2.33
    觔
    -2.20
     conosco
    -2.17
    ſelf
    -2.17
     начинают
    -2.17
    峮
    -2.16
    憮
    -2.14
    弍
    -2.09
    POSITIVE LOGITS
    ꪻ
    2.55
    iſter
    2.25
    ᯅ
    2.20
     یا
    2.13
    IANGLES
    2.05
    ⃢
    2.05
    怎样的
    2.02
     moderne
    2.02
    o
    2.00
    ꜆
    1.99
    Activations Density 0.003%

    No Known Activations