© 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. 22-GEMMASCOPE-RES-131K
    4. 67780
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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_22/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
    
    -1.05
    EFAULT
    -1.02
    }{$\
    -1.01
     awd
    -1.01
    ၜ
    -0.98
     vnnd
    -0.98
     Uttar
    -0.96
     prochaines
    -0.96
    delaide
    -0.95
     旗
    -0.94
    POSITIVE LOGITS
     съдържа
    0.98
    Especific
    0.98
    IDOS
    0.96
     хорошая
    0.96
    Однако
    0.95
    もあって
    0.94
    FFICIENT
    0.92
    がありますが
    0.91
    Heartbeat
    0.91
     entspre
    0.91
    Activations Density 0.001%

    No Known Activations