© 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. 10-GEMMASCOPE-RES-131K
    4. 123881
    Prev
    Next
    INDEX
    Explanations

    configuration parameters

    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
     séjours
    -2.22
    樯
    -1.96
     semblent
    -1.95
     Anſ
    -1.90
     Atención
    -1.89
     suppos
    -1.87
    丝毫
    -1.84
    Hå
    -1.84
     querían
    -1.83
    姈
    -1.83
    POSITIVE LOGITS
     first
    2.47
    In
    2.19
    </h2>
    2.08
    ↵↵
    2.05
     two
    1.90
    "
    1.90
     three
    1.88
     had
    1.86
     very
    1.86
            
    1.85
    Activations Density 0.011%

    No Known Activations