© 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. 290
    Prev
    Next
    INDEX
    Explanations

    Jordan names and associated entities

    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
    纮
    -2.66
     but
    -2.58
     Now
    -2.50
    瑨
    -2.45
     самая
    -2.36
    
    -2.34
     unsuitable
    -2.33
     This
    -2.30
     juzg
    -2.28
    ?'
    -2.25
    POSITIVE LOGITS
    牁
    2.67
    さらに
    2.64
    殽
    2.58
    Just
    2.44
     faſt
    2.39
     tetapi
    2.31
     tehdä
    2.25
    ﹍﹍
    2.23
    捋
    2.23
    So
    2.19
    Activations Density 0.005%

    No Known Activations