© 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. 20250
    Prev
    Next
    INDEX
    Explanations

    quality of life or service

    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
     This
    -2.97
     That
    -2.86
     Then
    -2.84
     Many
    -2.83
     Following
    -2.55
     permitirá
    -2.45
     With
    -2.41
    ſam
    -2.33
     You
    -2.33
     知道
    -2.31
    POSITIVE LOGITS
    e
    2.84
    every
    2.16
     последу
    2.13
    栳
    2.13
    ulates
    2.11
    𖤍
    2.08
    presented
    2.08
    ſu
    2.05
    حتى
    1.99
    Ито
    1.98
    Activations Density 0.006%

    No Known Activations