© 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. 66033
    Prev
    Next
    INDEX
    Explanations

    people named Ryan

    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
    ↵
    -3.61
    </h4>
    -2.97
    g
    -2.83
    </sup>
    -2.80
     we
    -2.58
    s
    -2.53
    </
    -2.50
    也
    -2.42
    ,"
    -2.42
     매우
    -2.41
    POSITIVE LOGITS
    笮
    2.81
    鳙
    2.59
    嵎
    2.59
    缛
    2.56
    しているので
    2.48
    деи
    2.48
    इटम
    2.45
    ༵
    2.42
    糗
    2.41
    してた
    2.36
    Activations Density 0.006%

    No Known Activations