© 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. 118800
    Prev
    Next
    INDEX
    Explanations

    Ill followed by ma, fro, ., us, try

    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
    以上です
    -2.98
    阄
    -2.86
    
    -2.80
    蹀
    -2.67
     лучший
    -2.59
     साल
    -2.50
    迨
    -2.48
    当代
    -2.48
    觏
    -2.48
    卌
    -2.47
    POSITIVE LOGITS
     This
    3.41
     He
    3.06
    .
    2.69
     was
    2.55
    ?"
    2.45
     Use
    2.42
     Then
    2.33
     That
    2.33
    l
    2.20
     bellezza
    2.11
    Activations Density 0.009%

    No Known Activations