© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25687
    Prev
    Next
    INDEX
    Explanations

    caused by

    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_34/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
    做到
    -1.03
    ClientRect
    -1.00
    ContentLoaded
    -0.85
     kilomet
    -0.82
     nhat
    -0.82
    ждены
    -0.82
     pione
    -0.82
    čko
    -0.79
    すけ
    -0.79
    èmes
    -0.78
    POSITIVE LOGITS
     caused
    1.50
     due
    1.46
     by
    1.39
     cause
    1.28
     solely
    1.23
     Caused
    1.16
     primarily
    1.16
     Causes
    1.14
     mainly
    1.14
     causes
    1.14
    Activations Density 0.067%

    No Known Activations