© 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. 19650
    Prev
    Next
    INDEX
    Explanations

    limiting factor or step

    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
     Inſ
    -2.45
     erhi
    -2.36
    景色
    -2.28
    
    -2.25
     minggu
    -2.25
    lahraga
    -2.25
     Hardly
    -2.20
    
    -2.20
    "—
    -2.17
     eminently
    -2.17
    POSITIVE LOGITS
    the
    2.83
    ).
    2.80
     choose
    2.75
    蛧
    2.69
    辔
    2.67
    when
    2.66
    颺
    2.64
     has
    2.64
    d
    2.59
    
    2.58
    Activations Density 0.025%

    No Known Activations