© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100754
    Prev
    Next
    INDEX
    Explanations

    of followed by determiners

    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
    ↵↵
    -2.13
    </h4>
    -1.95
     dunklen
    -1.80
    愎
    -1.79
     upheaval
    -1.74
     unruly
    -1.73
     eigentlichen
    -1.73
    邉
    -1.70
     unrelenting
    -1.69
    ）
    -1.67
    POSITIVE LOGITS
    ჱ
    2.02
    genodigd
    1.89
    觏
    1.87
     moft
    1.86
    
    1.84
     dieß
    1.80
    )
    1.80
     歯
    1.78
    哢
    1.76
     of
    1.74
    Activations Density 0.010%

    No Known Activations